iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Lots of exciting things this time!

Browse Source 
- support for rbd object-map and fast-diff features (myself).  This
   will speed up reads, discards and things like snap diffs on sparse
   images.
 
 - ceph.snap.btime vxattr to expose snapshot creation time (David
   Disseldorp).  This will be used to integrate with "Restore Previous
   Versions" feature added in Windows 7 for folks who reexport ceph
   through SMB.
 
 - security xattrs for ceph (Zheng Yan).  Only selinux is supported
   for now due to the limitations of ->dentry_init_security().
 
 - support for MSG_ADDR2, FS_BTIME and FS_CHANGE_ATTR features (Jeff
   Layton).  This is actually a single feature bit which was missing
   because of the filesystem pieces.  With this in, the kernel client
   will finally be reported as "luminous" by "ceph features" -- it is
   still being reported as "jewel" even though all required Luminous
   features were implemented in 4.13.
 
 - stop NULL-terminating ceph vxattrs (Jeff Layton).  The convention
   with xattrs is to not terminate and this was causing inconsistencies
   with ceph-fuse.
 
 - change filesystem time granularity from 1 us to 1 ns, again fixing
   an inconsistency with ceph-fuse (Luis Henriques).
 
 On top of this there are some additional dentry name handling and cap
 flushing fixes from Zheng.  Finally, Jeff is formally taking over for
 Zheng as the filesystem maintainer.
 -----BEGIN PGP SIGNATURE-----
 
 iQFHBAABCAAxFiEEydHwtzie9C7TfviiSn/eOAIR84sFAl0u+X8THGlkcnlvbW92
 QGdtYWlsLmNvbQAKCRBKf944AhHzi9byB/9fIxzoxtDMvixtJabuGSJRtlijDlWF
 GlO6yIWCXl/8v8easR2PCF75U/xv0+QFQmze8PVi8u4Xz589P247NnEuyEZ9n84i
 aCavARho6QLZPEL+B04NaqoHBl+ORKQTA6eKGhyKwRp/rn83z5Ubuw2tN7krHT3b
 kCY61FuTQGxNY2o/WKv/iLwINYr7H23hCf0WwyyKH1bp7OegiQ14Ebn1NtfS3sMx
 hS6h8Ya826vmUW0bCSS/9kzKYBCjksTig0HphUOHq6BoZJs++0b7GukIulRyuLfD
 J9Gr9HGPoDCVzdmFfpn2FSlxdmqfO9amUSagd0ftLQfFlPlrpoULi0GW
 =Bgxr
 -----END PGP SIGNATURE-----

Merge tag 'ceph-for-5.3-rc1' of git://github.com/ceph/ceph-client

Pull ceph updates from Ilya Dryomov:
 "Lots of exciting things this time!

   - support for rbd object-map and fast-diff features (myself). This
     will speed up reads, discards and things like snap diffs on sparse
     images.

   - ceph.snap.btime vxattr to expose snapshot creation time (David
     Disseldorp). This will be used to integrate with "Restore Previous
     Versions" feature added in Windows 7 for folks who reexport ceph
     through SMB.

   - security xattrs for ceph (Zheng Yan). Only selinux is supported for
     now due to the limitations of ->dentry_init_security().

   - support for MSG_ADDR2, FS_BTIME and FS_CHANGE_ATTR features (Jeff
     Layton). This is actually a single feature bit which was missing
     because of the filesystem pieces. With this in, the kernel client
     will finally be reported as "luminous" by "ceph features" -- it is
     still being reported as "jewel" even though all required Luminous
     features were implemented in 4.13.

   - stop NULL-terminating ceph vxattrs (Jeff Layton). The convention
     with xattrs is to not terminate and this was causing
     inconsistencies with ceph-fuse.

   - change filesystem time granularity from 1 us to 1 ns, again fixing
     an inconsistency with ceph-fuse (Luis Henriques).

  On top of this there are some additional dentry name handling and cap
  flushing fixes from Zheng. Finally, Jeff is formally taking over for
  Zheng as the filesystem maintainer"

* tag 'ceph-for-5.3-rc1' of git://github.com/ceph/ceph-client: (71 commits)
  ceph: fix end offset in truncate_inode_pages_range call
  ceph: use generic_delete_inode() for ->drop_inode
  ceph: use ceph_evict_inode to cleanup inode's resource
  ceph: initialize superblock s_time_gran to 1
  MAINTAINERS: take over for Zheng as CephFS kernel client maintainer
  rbd: setallochint only if object doesn't exist
  rbd: support for object-map and fast-diff
  rbd: call rbd_dev_mapping_set() from rbd_dev_image_probe()
  libceph: export osd_req_op_data() macro
  libceph: change ceph_osdc_call() to take page vector for response
  libceph: bump CEPH_MSG_MAX_DATA_LEN (again)
  rbd: new exclusive lock wait/wake code
  rbd: quiescing lock should wait for image requests
  rbd: lock should be quiesced on reacquire
  rbd: introduce copyup state machine
  rbd: rename rbd_obj_setup_*() to rbd_obj_init_*()
  rbd: move OSD request allocation into object request state machines
  rbd: factor out __rbd_osd_setup_discard_ops()
  rbd: factor out rbd_osd_setup_copyup()
  rbd: introduce obj_req->osd_reqs list
  ...
This commit is contained in:
Linus Torvalds 2019-07-18 11:05:25 -07:00
commit d9b9c89304
38 changed files with 2641 additions and 1162 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
MAINTAINERS
View File

@ -3765,7 +3765,7 @@ F: arch/powerpc/platforms/cell/
CEPH COMMON CODE (LIBCEPH)
M: Ilya Dryomov <idryomov@gmail.com>
M: "Yan, Zheng" <zyan@redhat.com>
M: Jeff Layton <jlayton@kernel.org>
M: Sage Weil <sage@redhat.com>
L: ceph-devel@vger.kernel.org
W: http://ceph.com/
@ -3777,7 +3777,7 @@ F: include/linux/ceph/
F: include/linux/crush/
CEPH DISTRIBUTED FILE SYSTEM CLIENT (CEPH)
M: "Yan, Zheng" <zyan@redhat.com>
M: Jeff Layton <jlayton@kernel.org>
M: Sage Weil <sage@redhat.com>
M: Ilya Dryomov <idryomov@gmail.com>
L: ceph-devel@vger.kernel.org

2218
drivers/block/rbd.c
View File

File diff suppressed because it is too large Load Diff

10
drivers/block/rbd_types.h
View File

@ -18,6 +18,7 @@
/* For format version 2, rbd image 'foo' consists of objects
* rbd_id.foo - id of image
* rbd_header.<id> - image metadata
* rbd_object_map.<id> - optional image object map
* rbd_data.<id>.0000000000000000
* rbd_data.<id>.0000000000000001
* ... - data
@ -25,6 +26,7 @@
*/
#define RBD_HEADER_PREFIX "rbd_header."
#define RBD_OBJECT_MAP_PREFIX "rbd_object_map."
#define RBD_ID_PREFIX "rbd_id."
#define RBD_V2_DATA_FORMAT "%s.%016llx"
@ -39,6 +41,14 @@ enum rbd_notify_op {
RBD_NOTIFY_OP_HEADER_UPDATE = 3,
};
#define OBJECT_NONEXISTENT 0
#define OBJECT_EXISTS 1
#define OBJECT_PENDING 2
#define OBJECT_EXISTS_CLEAN 3
#define RBD_FLAG_OBJECT_MAP_INVALID (1ULL << 0)
#define RBD_FLAG_FAST_DIFF_INVALID (1ULL << 1)
/*
* For format version 1, rbd image 'foo' consists of objects
* foo.rbd - image metadata

12
fs/ceph/Kconfig
View File

@ -36,3 +36,15 @@ config CEPH_FS_POSIX_ACL
groups beyond the owner/group/world scheme.
If you don't know what Access Control Lists are, say N
config CEPH_FS_SECURITY_LABEL
bool "CephFS Security Labels"
depends on CEPH_FS && SECURITY
help
Security labels support alternative access control models
implemented by security modules like SELinux. This option
enables an extended attribute handler for file security
labels in the Ceph filesystem.
If you are not using a security module that requires using
extended attributes for file security labels, say N.

22
fs/ceph/acl.c
View File

@ -159,7 +159,7 @@ out:
}
int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
struct ceph_acls_info *info)
struct ceph_acl_sec_ctx *as_ctx)
{
struct posix_acl *acl, *default_acl;
size_t val_size1 = 0, val_size2 = 0;
@ -234,9 +234,9 @@ int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
kfree(tmp_buf);
info->acl = acl;
info->default_acl = default_acl;
info->pagelist = pagelist;
as_ctx->acl = acl;
as_ctx->default_acl = default_acl;
as_ctx->pagelist = pagelist;
return 0;
out_err:
@ -248,18 +248,10 @@ out_err:
return err;
}
void ceph_init_inode_acls(struct inode* inode, struct ceph_acls_info *info)
void ceph_init_inode_acls(struct inode *inode, struct ceph_acl_sec_ctx *as_ctx)
{
if (!inode)
return;
ceph_set_cached_acl(inode, ACL_TYPE_ACCESS, info->acl);
ceph_set_cached_acl(inode, ACL_TYPE_DEFAULT, info->default_acl);
}
void ceph_release_acls_info(struct ceph_acls_info *info)
{
posix_acl_release(info->acl);
posix_acl_release(info->default_acl);
if (info->pagelist)
ceph_pagelist_release(info->pagelist);
ceph_set_cached_acl(inode, ACL_TYPE_ACCESS, as_ctx->acl);
ceph_set_cached_acl(inode, ACL_TYPE_DEFAULT, as_ctx->default_acl);
}

2
fs/ceph/addr.c
View File

@ -10,6 +10,7 @@
#include <linux/pagevec.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/signal.h>
#include <linux/iversion.h>
#include "super.h"
#include "mds_client.h"
@ -1576,6 +1577,7 @@ static vm_fault_t ceph_page_mkwrite(struct vm_fault *vmf)
/* Update time before taking page lock */
file_update_time(vma->vm_file);
inode_inc_iversion_raw(inode);
do {
lock_page(page);

120
fs/ceph/caps.c
View File

@ -8,6 +8,7 @@
#include <linux/vmalloc.h>
#include <linux/wait.h>
#include <linux/writeback.h>
#include <linux/iversion.h>
#include "super.h"
#include "mds_client.h"
@ -1138,8 +1139,9 @@ struct cap_msg_args {
u64 ino, cid, follows;
u64 flush_tid, oldest_flush_tid, size, max_size;
u64 xattr_version;
u64 change_attr;
struct ceph_buffer *xattr_buf;
struct timespec64 atime, mtime, ctime;
struct timespec64 atime, mtime, ctime, btime;
int op, caps, wanted, dirty;
u32 seq, issue_seq, mseq, time_warp_seq;
u32 flags;
@ -1160,7 +1162,6 @@ static int send_cap_msg(struct cap_msg_args *arg)
struct ceph_msg *msg;
void *p;
size_t extra_len;
struct timespec64 zerotime = {0};
struct ceph_osd_client *osdc = &arg->session->s_mdsc->fsc->client->osdc;
dout("send_cap_msg %s %llx %llx caps %s wanted %s dirty %s"
@ -1245,15 +1246,10 @@ static int send_cap_msg(struct cap_msg_args *arg)
/* pool namespace (version 8) (mds always ignores this) */
ceph_encode_32(&p, 0);
/*
* btime and change_attr (version 9)
*
* We just zero these out for now, as the MDS ignores them unless
* the requisite feature flags are set (which we don't do yet).
*/
ceph_encode_timespec64(p, &zerotime);
/* btime and change_attr (version 9) */
ceph_encode_timespec64(p, &arg->btime);
p += sizeof(struct ceph_timespec);
ceph_encode_64(&p, 0);
ceph_encode_64(&p, arg->change_attr);
/* Advisory flags (version 10) */
ceph_encode_32(&p, arg->flags);
@ -1263,20 +1259,22 @@ static int send_cap_msg(struct cap_msg_args *arg)
}
/*
* Queue cap releases when an inode is dropped from our cache. Since
* inode is about to be destroyed, there is no need for i_ceph_lock.
* Queue cap releases when an inode is dropped from our cache.
*/
void __ceph_remove_caps(struct inode *inode)
void __ceph_remove_caps(struct ceph_inode_info *ci)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct rb_node *p;
/* lock i_ceph_lock, because ceph_d_revalidate(..., LOOKUP_RCU)
* may call __ceph_caps_issued_mask() on a freeing inode. */
spin_lock(&ci->i_ceph_lock);
p = rb_first(&ci->i_caps);
while (p) {
struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node);
p = rb_next(p);
__ceph_remove_cap(cap, true);
}
spin_unlock(&ci->i_ceph_lock);
}
/*
@ -1297,7 +1295,7 @@ void __ceph_remove_caps(struct inode *inode)
* caller should hold snap_rwsem (read), s_mutex.
*/
static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
int op, bool sync, int used, int want, int retain,
int op, int flags, int used, int want, int retain,
int flushing, u64 flush_tid, u64 oldest_flush_tid)
__releases(cap->ci->i_ceph_lock)
{
@ -1377,6 +1375,8 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
arg.mtime = inode->i_mtime;
arg.atime = inode->i_atime;
arg.ctime = inode->i_ctime;
arg.btime = ci->i_btime;
arg.change_attr = inode_peek_iversion_raw(inode);
arg.op = op;
arg.caps = cap->implemented;
@ -1393,12 +1393,19 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
arg.mode = inode->i_mode;
arg.inline_data = ci->i_inline_version != CEPH_INLINE_NONE;
if (list_empty(&ci->i_cap_snaps))
arg.flags = CEPH_CLIENT_CAPS_NO_CAPSNAP;
else
arg.flags = CEPH_CLIENT_CAPS_PENDING_CAPSNAP;
if (sync)
arg.flags |= CEPH_CLIENT_CAPS_SYNC;
if (!(flags & CEPH_CLIENT_CAPS_PENDING_CAPSNAP) &&
!list_empty(&ci->i_cap_snaps)) {
struct ceph_cap_snap *capsnap;
list_for_each_entry_reverse(capsnap, &ci->i_cap_snaps, ci_item) {
if (capsnap->cap_flush.tid)
break;
if (capsnap->need_flush) {
flags |= CEPH_CLIENT_CAPS_PENDING_CAPSNAP;
break;
}
}
}
arg.flags = flags;
spin_unlock(&ci->i_ceph_lock);
@ -1436,6 +1443,8 @@ static inline int __send_flush_snap(struct inode *inode,
arg.atime = capsnap->atime;
arg.mtime = capsnap->mtime;
arg.ctime = capsnap->ctime;
arg.btime = capsnap->btime;
arg.change_attr = capsnap->change_attr;
arg.op = CEPH_CAP_OP_FLUSHSNAP;
arg.caps = capsnap->issued;
@ -1603,10 +1612,8 @@ retry:
}
// make sure flushsnap messages are sent in proper order.
if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH) {
if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH)
__kick_flushing_caps(mdsc, session, ci, 0);
ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
}
__ceph_flush_snaps(ci, session);
out:
@ -2048,10 +2055,8 @@ ack:
if (cap == ci->i_auth_cap &&
(ci->i_ceph_flags &
(CEPH_I_KICK_FLUSH | CEPH_I_FLUSH_SNAPS))) {
if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH) {
if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH)
__kick_flushing_caps(mdsc, session, ci, 0);
ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
}
if (ci->i_ceph_flags & CEPH_I_FLUSH_SNAPS)
__ceph_flush_snaps(ci, session);
@ -2087,7 +2092,7 @@ ack:
sent++;
/* __send_cap drops i_ceph_lock */
delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, false,
delayed += __send_cap(mdsc, cap, CEPH_CAP_OP_UPDATE, 0,
cap_used, want, retain, flushing,
flush_tid, oldest_flush_tid);
goto retry; /* retake i_ceph_lock and restart our cap scan. */
@ -2121,6 +2126,7 @@ static int try_flush_caps(struct inode *inode, u64 *ptid)
retry:
spin_lock(&ci->i_ceph_lock);
retry_locked:
if (ci->i_ceph_flags & CEPH_I_NOFLUSH) {
spin_unlock(&ci->i_ceph_lock);
dout("try_flush_caps skipping %p I_NOFLUSH set\n", inode);
@ -2128,8 +2134,6 @@ retry:
}
if (ci->i_dirty_caps && ci->i_auth_cap) {
struct ceph_cap *cap = ci->i_auth_cap;
int used = __ceph_caps_used(ci);
int want = __ceph_caps_wanted(ci);
int delayed;
if (!session || session != cap->session) {
@ -2145,13 +2149,25 @@ retry:
goto out;
}
if (ci->i_ceph_flags &
(CEPH_I_KICK_FLUSH | CEPH_I_FLUSH_SNAPS)) {
if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH)
__kick_flushing_caps(mdsc, session, ci, 0);
if (ci->i_ceph_flags & CEPH_I_FLUSH_SNAPS)
__ceph_flush_snaps(ci, session);
goto retry_locked;
}
flushing = __mark_caps_flushing(inode, session, true,
&flush_tid, &oldest_flush_tid);
/* __send_cap drops i_ceph_lock */
delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH, true,
used, want, (cap->issued | cap->implemented),
flushing, flush_tid, oldest_flush_tid);
delayed = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
CEPH_CLIENT_CAPS_SYNC,
__ceph_caps_used(ci),
__ceph_caps_wanted(ci),
(cap->issued | cap->implemented),
flushing, flush_tid, oldest_flush_tid);
if (delayed) {
spin_lock(&ci->i_ceph_lock);
@ -2320,6 +2336,16 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
struct ceph_cap_flush *cf;
int ret;
u64 first_tid = 0;
u64 last_snap_flush = 0;
ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
list_for_each_entry_reverse(cf, &ci->i_cap_flush_list, i_list) {
if (!cf->caps) {
last_snap_flush = cf->tid;
break;
}
}
list_for_each_entry(cf, &ci->i_cap_flush_list, i_list) {
if (cf->tid < first_tid)
@ -2338,10 +2364,13 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
dout("kick_flushing_caps %p cap %p tid %llu %s\n",
inode, cap, cf->tid, ceph_cap_string(cf->caps));
ci->i_ceph_flags |= CEPH_I_NODELAY;
ret = __send_cap(mdsc, cap, CEPH_CAP_OP_FLUSH,
false, __ceph_caps_used(ci),
(cf->tid < last_snap_flush ?
CEPH_CLIENT_CAPS_PENDING_CAPSNAP : 0),
__ceph_caps_used(ci),
__ceph_caps_wanted(ci),
cap->issued | cap->implemented,
(cap->issued | cap->implemented),
cf->caps, cf->tid, oldest_flush_tid);
if (ret) {
pr_err("kick_flushing_caps: error sending "
@ -2410,7 +2439,6 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc,
*/
if ((cap->issued & ci->i_flushing_caps) !=
ci->i_flushing_caps) {
ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
/* encode_caps_cb() also will reset these sequence
* numbers. make sure sequence numbers in cap flush
* message match later reconnect message */
@ -2450,7 +2478,6 @@ void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc,
continue;
}
if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH) {
ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
__kick_flushing_caps(mdsc, session, ci,
oldest_flush_tid);
}
@ -2478,7 +2505,6 @@ static void kick_flushing_inode_caps(struct ceph_mds_client *mdsc,
oldest_flush_tid = __get_oldest_flush_tid(mdsc);
spin_unlock(&mdsc->cap_dirty_lock);
ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH;
__kick_flushing_caps(mdsc, session, ci, oldest_flush_tid);
spin_unlock(&ci->i_ceph_lock);
} else {
@ -3040,8 +3066,10 @@ struct cap_extra_info {
bool dirstat_valid;
u64 nfiles;
u64 nsubdirs;
u64 change_attr;
/* currently issued */
int issued;
struct timespec64 btime;
};
/*
@ -3123,11 +3151,14 @@ static void handle_cap_grant(struct inode *inode,
__check_cap_issue(ci, cap, newcaps);
inode_set_max_iversion_raw(inode, extra_info->change_attr);
if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
(extra_info->issued & CEPH_CAP_AUTH_EXCL) == 0) {
inode->i_mode = le32_to_cpu(grant->mode);
inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(grant->uid));
inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(grant->gid));
ci->i_btime = extra_info->btime;
dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
from_kuid(&init_user_ns, inode->i_uid),
from_kgid(&init_user_ns, inode->i_gid));
@ -3154,6 +3185,7 @@ static void handle_cap_grant(struct inode *inode,
ci->i_xattrs.blob = ceph_buffer_get(xattr_buf);
ci->i_xattrs.version = version;
ceph_forget_all_cached_acls(inode);
ceph_security_invalidate_secctx(inode);
}
}
@ -3848,17 +3880,19 @@ void ceph_handle_caps(struct ceph_mds_session *session,
}
}
if (msg_version >= 11) {
if (msg_version >= 9) {
struct ceph_timespec *btime;
u64 change_attr;
u32 flags;
/* version >= 9 */
if (p + sizeof(*btime) > end)
goto bad;
btime = p;
ceph_decode_timespec64(&extra_info.btime, btime);
p += sizeof(*btime);
ceph_decode_64_safe(&p, end, change_attr, bad);
ceph_decode_64_safe(&p, end, extra_info.change_attr, bad);
}
if (msg_version >= 11) {
u32 flags;
/* version >= 10 */
ceph_decode_32_safe(&p, end, flags, bad);
/* version >= 11 */

2
fs/ceph/debugfs.c
View File

@ -52,7 +52,7 @@ static int mdsc_show(struct seq_file *s, void *p)
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
struct rb_node *rp;
int pathlen;
int pathlen = 0;
u64 pathbase;
char *path;

73
fs/ceph/dir.c
View File

@ -825,7 +825,7 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
struct ceph_acls_info acls = {};
struct ceph_acl_sec_ctx as_ctx = {};
int err;
if (ceph_snap(dir) != CEPH_NOSNAP)
@ -836,7 +836,10 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
goto out;
}
err = ceph_pre_init_acls(dir, &mode, &acls);
err = ceph_pre_init_acls(dir, &mode, &as_ctx);
if (err < 0)
goto out;
err = ceph_security_init_secctx(dentry, mode, &as_ctx);
if (err < 0)
goto out;
@ -855,9 +858,9 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
req->r_args.mknod.rdev = cpu_to_le32(rdev);
req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
if (acls.pagelist) {
req->r_pagelist = acls.pagelist;
acls.pagelist = NULL;
if (as_ctx.pagelist) {
req->r_pagelist = as_ctx.pagelist;
as_ctx.pagelist = NULL;
}
err = ceph_mdsc_do_request(mdsc, dir, req);
if (!err && !req->r_reply_info.head->is_dentry)
@ -865,10 +868,10 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
ceph_mdsc_put_request(req);
out:
if (!err)
ceph_init_inode_acls(d_inode(dentry), &acls);
ceph_init_inode_acls(d_inode(dentry), &as_ctx);
else
d_drop(dentry);
ceph_release_acls_info(&acls);
ceph_release_acl_sec_ctx(&as_ctx);
return err;
}
@ -884,6 +887,7 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
struct ceph_acl_sec_ctx as_ctx = {};
int err;
if (ceph_snap(dir) != CEPH_NOSNAP)
@ -894,6 +898,10 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
goto out;
}
err = ceph_security_init_secctx(dentry, S_IFLNK | 0777, &as_ctx);
if (err < 0)
goto out;
dout("symlink in dir %p dentry %p to '%s'\n", dir, dentry, dest);
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SYMLINK, USE_AUTH_MDS);
if (IS_ERR(req)) {
@ -919,6 +927,7 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
out:
if (err)
d_drop(dentry);
ceph_release_acl_sec_ctx(&as_ctx);
return err;
}
@ -927,7 +936,7 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
struct ceph_acls_info acls = {};
struct ceph_acl_sec_ctx as_ctx = {};
int err = -EROFS;
int op;
@ -950,7 +959,10 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
}
mode |= S_IFDIR;
err = ceph_pre_init_acls(dir, &mode, &acls);
err = ceph_pre_init_acls(dir, &mode, &as_ctx);
if (err < 0)
goto out;
err = ceph_security_init_secctx(dentry, mode, &as_ctx);
if (err < 0)
goto out;
@ -967,9 +979,9 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
req->r_args.mkdir.mode = cpu_to_le32(mode);
req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
if (acls.pagelist) {
req->r_pagelist = acls.pagelist;
acls.pagelist = NULL;
if (as_ctx.pagelist) {
req->r_pagelist = as_ctx.pagelist;
as_ctx.pagelist = NULL;
}
err = ceph_mdsc_do_request(mdsc, dir, req);
if (!err &&
@ -979,10 +991,10 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
ceph_mdsc_put_request(req);
out:
if (!err)
ceph_init_inode_acls(d_inode(dentry), &acls);
ceph_init_inode_acls(d_inode(dentry), &as_ctx);
else
d_drop(dentry);
ceph_release_acls_info(&acls);
ceph_release_acl_sec_ctx(&as_ctx);
return err;
}
@ -1433,8 +1445,7 @@ static bool __dentry_lease_is_valid(struct ceph_dentry_info *di)
return false;
}
static int dentry_lease_is_valid(struct dentry *dentry, unsigned int flags,
struct inode *dir)
static int dentry_lease_is_valid(struct dentry *dentry, unsigned int flags)
{
struct ceph_dentry_info *di;
struct ceph_mds_session *session = NULL;
@ -1466,7 +1477,7 @@ static int dentry_lease_is_valid(struct dentry *dentry, unsigned int flags,
spin_unlock(&dentry->d_lock);
if (session) {
ceph_mdsc_lease_send_msg(session, dir, dentry,
ceph_mdsc_lease_send_msg(session, dentry,
CEPH_MDS_LEASE_RENEW, seq);
ceph_put_mds_session(session);
}
@ -1512,18 +1523,26 @@ static int __dir_lease_try_check(const struct dentry *dentry)
static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry)
{
struct ceph_inode_info *ci = ceph_inode(dir);
struct ceph_dentry_info *di = ceph_dentry(dentry);
int valid = 0;
int valid;
int shared_gen;
spin_lock(&ci->i_ceph_lock);
if (atomic_read(&ci->i_shared_gen) == di->lease_shared_gen)
valid = __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1);
valid = __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1);
shared_gen = atomic_read(&ci->i_shared_gen);
spin_unlock(&ci->i_ceph_lock);
if (valid)
__ceph_dentry_dir_lease_touch(di);
dout("dir_lease_is_valid dir %p v%u dentry %p v%u = %d\n",
dir, (unsigned)atomic_read(&ci->i_shared_gen),
dentry, (unsigned)di->lease_shared_gen, valid);
if (valid) {
struct ceph_dentry_info *di;
spin_lock(&dentry->d_lock);
di = ceph_dentry(dentry);
if (dir == d_inode(dentry->d_parent) &&
di && di->lease_shared_gen == shared_gen)
__ceph_dentry_dir_lease_touch(di);
else
valid = 0;
spin_unlock(&dentry->d_lock);
}
dout("dir_lease_is_valid dir %p v%u dentry %p = %d\n",
dir, (unsigned)atomic_read(&ci->i_shared_gen), dentry, valid);
return valid;
}
@ -1558,7 +1577,7 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
ceph_snap(d_inode(dentry)) == CEPH_SNAPDIR) {
valid = 1;
} else {
valid = dentry_lease_is_valid(dentry, flags, dir);
valid = dentry_lease_is_valid(dentry, flags);
if (valid == -ECHILD)
return valid;
if (valid || dir_lease_is_valid(dir, dentry)) {

2
fs/ceph/export.c
View File

@ -368,7 +368,7 @@ static struct dentry *ceph_get_parent(struct dentry *child)
}
out:
dout("get_parent %p ino %llx.%llx err=%ld\n",
child, ceph_vinop(inode), (IS_ERR(dn) ? PTR_ERR(dn) : 0));
child, ceph_vinop(inode), (long)PTR_ERR_OR_ZERO(dn));
return dn;
}

34
fs/ceph/file.c
View File

@ -10,6 +10,7 @@
#include <linux/namei.h>
#include <linux/writeback.h>
#include <linux/falloc.h>
#include <linux/iversion.h>
#include "super.h"
#include "mds_client.h"
@ -437,7 +438,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
struct ceph_mds_client *mdsc = fsc->mdsc;
struct ceph_mds_request *req;
struct dentry *dn;
struct ceph_acls_info acls = {};
struct ceph_acl_sec_ctx as_ctx = {};
int mask;
int err;
@ -451,25 +452,28 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
if (flags & O_CREAT) {
if (ceph_quota_is_max_files_exceeded(dir))
return -EDQUOT;
err = ceph_pre_init_acls(dir, &mode, &acls);
err = ceph_pre_init_acls(dir, &mode, &as_ctx);
if (err < 0)
return err;
err = ceph_security_init_secctx(dentry, mode, &as_ctx);
if (err < 0)
goto out_ctx;
}
/* do the open */
req = prepare_open_request(dir->i_sb, flags, mode);
if (IS_ERR(req)) {
err = PTR_ERR(req);
goto out_acl;
goto out_ctx;
}
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
if (flags & O_CREAT) {
req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL;
req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
if (acls.pagelist) {
req->r_pagelist = acls.pagelist;
acls.pagelist = NULL;
if (as_ctx.pagelist) {
req->r_pagelist = as_ctx.pagelist;
as_ctx.pagelist = NULL;
}
}
@ -507,7 +511,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
} else {
dout("atomic_open finish_open on dn %p\n", dn);
if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
ceph_init_inode_acls(d_inode(dentry), &acls);
ceph_init_inode_acls(d_inode(dentry), &as_ctx);
file->f_mode |= FMODE_CREATED;
}
err = finish_open(file, dentry, ceph_open);
@ -516,8 +520,8 @@ out_req:
if (!req->r_err && req->r_target_inode)
ceph_put_fmode(ceph_inode(req->r_target_inode), req->r_fmode);
ceph_mdsc_put_request(req);
out_acl:
ceph_release_acls_info(&acls);
out_ctx:
ceph_release_acl_sec_ctx(&as_ctx);
dout("atomic_open result=%d\n", err);
return err;
}
@ -1007,7 +1011,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
* may block.
*/
truncate_inode_pages_range(inode->i_mapping, pos,
(pos+len) | (PAGE_SIZE - 1));
PAGE_ALIGN(pos + len) - 1);
req->r_mtime = mtime;
}
@ -1022,7 +1026,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
req->r_callback = ceph_aio_complete_req;
req->r_inode = inode;
req->r_priv = aio_req;
list_add_tail(&req->r_unsafe_item, &aio_req->osd_reqs);
list_add_tail(&req->r_private_item, &aio_req->osd_reqs);
pos += len;
continue;
@ -1082,8 +1086,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
while (!list_empty(&osd_reqs)) {
req = list_first_entry(&osd_reqs,
struct ceph_osd_request,
r_unsafe_item);
list_del_init(&req->r_unsafe_item);
r_private_item);
list_del_init(&req->r_private_item);
if (ret >= 0)
ret = ceph_osdc_start_request(req->r_osdc,
req, false);
@ -1432,6 +1436,8 @@ retry_snap:
if (err)
goto out;
inode_inc_iversion_raw(inode);
if (ci->i_inline_version != CEPH_INLINE_NONE) {
err = ceph_uninline_data(file, NULL);
if (err < 0)
@ -2063,6 +2069,8 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
do_final_copy = true;
file_update_time(dst_file);
inode_inc_iversion_raw(dst_inode);
if (endoff > size) {
int caps_flags = 0;

208
fs/ceph/inode.c
View File

@ -13,6 +13,7 @@
#include <linux/posix_acl.h>
#include <linux/random.h>
#include <linux/sort.h>
#include <linux/iversion.h>
#include "super.h"
#include "mds_client.h"
@ -42,6 +43,7 @@ static int ceph_set_ino_cb(struct inode *inode, void *data)
{
ceph_inode(inode)->i_vino = *(struct ceph_vino *)data;
inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data);
inode_set_iversion_raw(inode, 0);
return 0;
}
@ -509,6 +511,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
INIT_WORK(&ci->i_work, ceph_inode_work);
ci->i_work_mask = 0;
memset(&ci->i_btime, '\0', sizeof(ci->i_btime));
ceph_fscache_inode_init(ci);
@ -523,17 +526,20 @@ void ceph_free_inode(struct inode *inode)
kmem_cache_free(ceph_inode_cachep, ci);
}
void ceph_destroy_inode(struct inode *inode)
void ceph_evict_inode(struct inode *inode)
{
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_inode_frag *frag;
struct rb_node *n;
dout("destroy_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode));
dout("evict_inode %p ino %llx.%llx\n", inode, ceph_vinop(inode));
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
ceph_fscache_unregister_inode_cookie(ci);
__ceph_remove_caps(inode);
__ceph_remove_caps(ci);
if (__ceph_has_any_quota(ci))
ceph_adjust_quota_realms_count(inode, false);
@ -578,16 +584,6 @@ void ceph_destroy_inode(struct inode *inode)
ceph_put_string(rcu_dereference_raw(ci->i_layout.pool_ns));
}
int ceph_drop_inode(struct inode *inode)
{
/*
* Positve dentry and corresponding inode are always accompanied
* in MDS reply. So no need to keep inode in the cache after
* dropping all its aliases.
*/
return 1;
}
static inline blkcnt_t calc_inode_blocks(u64 size)
{
return (size + (1<<9) - 1) >> 9;
@ -795,6 +791,9 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
le64_to_cpu(info->version) > (ci->i_version & ~1)))
new_version = true;
/* Update change_attribute */
inode_set_max_iversion_raw(inode, iinfo->change_attr);
__ceph_caps_issued(ci, &issued);
issued |= __ceph_caps_dirty(ci);
new_issued = ~issued & info_caps;
@ -813,6 +812,8 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
dout("%p mode 0%o uid.gid %d.%d\n", inode, inode->i_mode,
from_kuid(&init_user_ns, inode->i_uid),
from_kgid(&init_user_ns, inode->i_gid));
ceph_decode_timespec64(&ci->i_btime, &iinfo->btime);
ceph_decode_timespec64(&ci->i_snap_btime, &iinfo->snap_btime);
}
if ((new_version || (new_issued & CEPH_CAP_LINK_SHARED)) &&
@ -887,6 +888,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,
iinfo->xattr_data, iinfo->xattr_len);
ci->i_xattrs.version = le64_to_cpu(info->xattr_version);
ceph_forget_all_cached_acls(inode);
ceph_security_invalidate_secctx(inode);
xattr_blob = NULL;
}
@ -1027,59 +1029,38 @@ out:
}
/*
* caller should hold session s_mutex.
* caller should hold session s_mutex and dentry->d_lock.
*/
static void update_dentry_lease(struct dentry *dentry,
struct ceph_mds_reply_lease *lease,
struct ceph_mds_session *session,
unsigned long from_time,
struct ceph_vino *tgt_vino,
struct ceph_vino *dir_vino)
static void __update_dentry_lease(struct inode *dir, struct dentry *dentry,
struct ceph_mds_reply_lease *lease,
struct ceph_mds_session *session,
unsigned long from_time,
struct ceph_mds_session **old_lease_session)
{
struct ceph_dentry_info *di = ceph_dentry(dentry);
long unsigned duration = le32_to_cpu(lease->duration_ms);
long unsigned ttl = from_time + (duration * HZ) / 1000;
long unsigned half_ttl = from_time + (duration * HZ / 2) / 1000;
struct inode *dir;
struct ceph_mds_session *old_lease_session = NULL;
/*
* Make sure dentry's inode matches tgt_vino. NULL tgt_vino means that
* we expect a negative dentry.
*/
if (!tgt_vino && d_really_is_positive(dentry))
return;
if (tgt_vino && (d_really_is_negative(dentry) ||
!ceph_ino_compare(d_inode(dentry), tgt_vino)))
return;
spin_lock(&dentry->d_lock);
dout("update_dentry_lease %p duration %lu ms ttl %lu\n",
dentry, duration, ttl);
dir = d_inode(dentry->d_parent);
/* make sure parent matches dir_vino */
if (!ceph_ino_compare(dir, dir_vino))
goto out_unlock;
/* only track leases on regular dentries */
if (ceph_snap(dir) != CEPH_NOSNAP)
goto out_unlock;
return;
di->lease_shared_gen = atomic_read(&ceph_inode(dir)->i_shared_gen);
if (duration == 0) {
__ceph_dentry_dir_lease_touch(di);
goto out_unlock;
return;
}
if (di->lease_gen == session->s_cap_gen &&
time_before(ttl, di->time))
goto out_unlock; /* we already have a newer lease. */
return; /* we already have a newer lease. */
if (di->lease_session && di->lease_session != session) {
old_lease_session = di->lease_session;
*old_lease_session = di->lease_session;
di->lease_session = NULL;
}
@ -1092,6 +1073,62 @@ static void update_dentry_lease(struct dentry *dentry,
di->time = ttl;
__ceph_dentry_lease_touch(di);
}
static inline void update_dentry_lease(struct inode *dir, struct dentry *dentry,
struct ceph_mds_reply_lease *lease,
struct ceph_mds_session *session,
unsigned long from_time)
{
struct ceph_mds_session *old_lease_session = NULL;
spin_lock(&dentry->d_lock);
__update_dentry_lease(dir, dentry, lease, session, from_time,
&old_lease_session);
spin_unlock(&dentry->d_lock);
if (old_lease_session)
ceph_put_mds_session(old_lease_session);
}
/*
* update dentry lease without having parent inode locked
*/
static void update_dentry_lease_careful(struct dentry *dentry,
struct ceph_mds_reply_lease *lease,
struct ceph_mds_session *session,
unsigned long from_time,
char *dname, u32 dname_len,
struct ceph_vino *pdvino,
struct ceph_vino *ptvino)
{
struct inode *dir;
struct ceph_mds_session *old_lease_session = NULL;
spin_lock(&dentry->d_lock);
/* make sure dentry's name matches target */
if (dentry->d_name.len != dname_len ||
memcmp(dentry->d_name.name, dname, dname_len))
goto out_unlock;
dir = d_inode(dentry->d_parent);
/* make sure parent matches dvino */
if (!ceph_ino_compare(dir, pdvino))
goto out_unlock;
/* make sure dentry's inode matches target. NULL ptvino means that
* we expect a negative dentry */
if (ptvino) {
if (d_really_is_negative(dentry))
goto out_unlock;
if (!ceph_ino_compare(d_inode(dentry), ptvino))
goto out_unlock;
} else {
if (d_really_is_positive(dentry))
goto out_unlock;
}
__update_dentry_lease(dir, dentry, lease, session,
from_time, &old_lease_session);
out_unlock:
spin_unlock(&dentry->d_lock);
if (old_lease_session)
@ -1156,19 +1193,6 @@ static int splice_dentry(struct dentry **pdn, struct inode *in)
return 0;
}
static int d_name_cmp(struct dentry *dentry, const char *name, size_t len)
{
int ret;
/* take d_lock to ensure dentry->d_name stability */
spin_lock(&dentry->d_lock);
ret = dentry->d_name.len - len;
if (!ret)
ret = memcmp(dentry->d_name.name, name, len);
spin_unlock(&dentry->d_lock);
return ret;
}
/*
* Incorporate results into the local cache. This is either just
* one inode, or a directory, dentry, and possibly linked-to inode (e.g.,
@ -1371,10 +1395,9 @@ retry_lookup:
} else if (have_lease) {
if (d_unhashed(dn))
d_add(dn, NULL);
update_dentry_lease(dn, rinfo->dlease,
session,
req->r_request_started,
NULL, &dvino);
update_dentry_lease(dir, dn,
rinfo->dlease, session,
req->r_request_started);
}
goto done;
}
@ -1396,11 +1419,9 @@ retry_lookup:
}
if (have_lease) {
tvino.ino = le64_to_cpu(rinfo->targeti.in->ino);
tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
update_dentry_lease(dn, rinfo->dlease, session,
req->r_request_started,
&tvino, &dvino);
update_dentry_lease(dir, dn,
rinfo->dlease, session,
req->r_request_started);
}
dout(" final dn %p\n", dn);
} else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
@ -1418,27 +1439,20 @@ retry_lookup:
err = splice_dentry(&req->r_dentry, in);
if (err < 0)
goto done;
} else if (rinfo->head->is_dentry &&
!d_name_cmp(req->r_dentry, rinfo->dname, rinfo->dname_len)) {
} else if (rinfo->head->is_dentry && req->r_dentry) {
/* parent inode is not locked, be carefull */
struct ceph_vino *ptvino = NULL;
if ((le32_to_cpu(rinfo->diri.in->cap.caps) & CEPH_CAP_FILE_SHARED) ||
le32_to_cpu(rinfo->dlease->duration_ms)) {
dvino.ino = le64_to_cpu(rinfo->diri.in->ino);
dvino.snap = le64_to_cpu(rinfo->diri.in->snapid);
if (rinfo->head->is_target) {
tvino.ino = le64_to_cpu(rinfo->targeti.in->ino);
tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
ptvino = &tvino;
}
update_dentry_lease(req->r_dentry, rinfo->dlease,
session, req->r_request_started, ptvino,
&dvino);
} else {
dout("%s: no dentry lease or dir cap\n", __func__);
dvino.ino = le64_to_cpu(rinfo->diri.in->ino);
dvino.snap = le64_to_cpu(rinfo->diri.in->snapid);
if (rinfo->head->is_target) {
tvino.ino = le64_to_cpu(rinfo->targeti.in->ino);
tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
ptvino = &tvino;
}
update_dentry_lease_careful(req->r_dentry, rinfo->dlease,
session, req->r_request_started,
rinfo->dname, rinfo->dname_len,
&dvino, ptvino);
}
done:
dout("fill_trace done err=%d\n", err);
@ -1600,7 +1614,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
/* FIXME: release caps/leases if error occurs */
for (i = 0; i < rinfo->dir_nr; i++) {
struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
struct ceph_vino tvino, dvino;
struct ceph_vino tvino;
dname.name = rde->name;
dname.len = rde->name_len;
@ -1701,9 +1715,9 @@ retry_lookup:
ceph_dentry(dn)->offset = rde->offset;
dvino = ceph_vino(d_inode(parent));
update_dentry_lease(dn, rde->lease, req->r_session,
req->r_request_started, &tvino, &dvino);
update_dentry_lease(d_inode(parent), dn,
rde->lease, req->r_session,
req->r_request_started);
if (err == 0 && skipped == 0 && cache_ctl.index >= 0) {
ret = fill_readdir_cache(d_inode(parent), dn,
@ -2282,7 +2296,7 @@ static int statx_to_caps(u32 want)
{
int mask = 0;
if (want & (STATX_MODE|STATX_UID|STATX_GID|STATX_CTIME))
if (want & (STATX_MODE|STATX_UID|STATX_GID|STATX_CTIME|STATX_BTIME))
mask |= CEPH_CAP_AUTH_SHARED;
if (want & (STATX_NLINK|STATX_CTIME))
@ -2307,6 +2321,7 @@ int ceph_getattr(const struct path *path, struct kstat *stat,
{
struct inode *inode = d_inode(path->dentry);
struct ceph_inode_info *ci = ceph_inode(inode);
u32 valid_mask = STATX_BASIC_STATS;
int err = 0;
/* Skip the getattr altogether if we're asked not to sync */
@ -2319,6 +2334,16 @@ int ceph_getattr(const struct path *path, struct kstat *stat,
generic_fillattr(inode, stat);
stat->ino = ceph_translate_ino(inode->i_sb, inode->i_ino);
/*
* btime on newly-allocated inodes is 0, so if this is still set to
* that, then assume that it's not valid.
*/
if (ci->i_btime.tv_sec || ci->i_btime.tv_nsec) {
stat->btime = ci->i_btime;
valid_mask |= STATX_BTIME;
}
if (ceph_snap(inode) == CEPH_NOSNAP)
stat->dev = inode->i_sb->s_dev;
else
@ -2342,7 +2367,6 @@ int ceph_getattr(const struct path *path, struct kstat *stat,
stat->nlink = 1 + 1 + ci->i_subdirs;
}
/* Mask off any higher bits (e.g. btime) until we have support */
stat->result_mask = request_mask & STATX_BASIC_STATS;
stat->result_mask = request_mask & valid_mask;
return err;
}

122
fs/ceph/mds_client.c
View File

@ -150,14 +150,13 @@ static int parse_reply_info_in(void **p, void *end,
info->pool_ns_data = *p;
*p += info->pool_ns_len;
}
/* btime, change_attr */
{
struct ceph_timespec btime;
u64 change_attr;
ceph_decode_need(p, end, sizeof(btime), bad);
ceph_decode_copy(p, &btime, sizeof(btime));
ceph_decode_64_safe(p, end, change_attr, bad);
}
/* btime */
ceph_decode_need(p, end, sizeof(info->btime), bad);
ceph_decode_copy(p, &info->btime, sizeof(info->btime));
/* change attribute */
ceph_decode_64_safe(p, end, info->change_attr, bad);
/* dir pin */
if (struct_v >= 2) {
@ -166,6 +165,15 @@ static int parse_reply_info_in(void **p, void *end,
info->dir_pin = -ENODATA;
}
/* snapshot birth time, remains zero for v<=2 */
if (struct_v >= 3) {
ceph_decode_need(p, end, sizeof(info->snap_btime), bad);
ceph_decode_copy(p, &info->snap_btime,
sizeof(info->snap_btime));
} else {
memset(&info->snap_btime, 0, sizeof(info->snap_btime));
}
*p = end;
} else {
if (features & CEPH_FEATURE_MDS_INLINE_DATA) {
@ -197,7 +205,14 @@ static int parse_reply_info_in(void **p, void *end,
}
}
if (features & CEPH_FEATURE_FS_BTIME) {
ceph_decode_need(p, end, sizeof(info->btime), bad);
ceph_decode_copy(p, &info->btime, sizeof(info->btime));
ceph_decode_64_safe(p, end, info->change_attr, bad);
}
info->dir_pin = -ENODATA;
/* info->snap_btime remains zero */
}
return 0;
bad:
@ -717,6 +732,7 @@ void ceph_mdsc_release_request(struct kref *kref)
ceph_pagelist_release(req->r_pagelist);
put_request_session(req);
ceph_unreserve_caps(req->r_mdsc, &req->r_caps_reservation);
WARN_ON_ONCE(!list_empty(&req->r_wait));
kfree(req);
}
@ -903,7 +919,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
struct inode *dir;
rcu_read_lock();
parent = req->r_dentry->d_parent;
parent = READ_ONCE(req->r_dentry->d_parent);
dir = req->r_parent ? : d_inode_rcu(parent);
if (!dir || dir->i_sb != mdsc->fsc->sb) {
@ -2135,7 +2151,7 @@ retry:
memcpy(path + pos, temp->d_name.name, temp->d_name.len);
}
spin_unlock(&temp->d_lock);
temp = temp->d_parent;
temp = READ_ONCE(temp->d_parent);
/* Are we at the root? */
if (IS_ROOT(temp))
@ -3727,42 +3743,35 @@ static void check_new_map(struct ceph_mds_client *mdsc,
ceph_mdsmap_is_laggy(newmap, i) ? " (laggy)" : "",
ceph_session_state_name(s->s_state));
if (i >= newmap->m_num_mds ||
memcmp(ceph_mdsmap_get_addr(oldmap, i),
if (i >= newmap->m_num_mds) {
/* force close session for stopped mds */
get_session(s);
__unregister_session(mdsc, s);
__wake_requests(mdsc, &s->s_waiting);
mutex_unlock(&mdsc->mutex);
mutex_lock(&s->s_mutex);
cleanup_session_requests(mdsc, s);
remove_session_caps(s);
mutex_unlock(&s->s_mutex);
ceph_put_mds_session(s);
mutex_lock(&mdsc->mutex);
kick_requests(mdsc, i);
continue;
}
if (memcmp(ceph_mdsmap_get_addr(oldmap, i),
ceph_mdsmap_get_addr(newmap, i),
sizeof(struct ceph_entity_addr))) {
if (s->s_state == CEPH_MDS_SESSION_OPENING) {
/* the session never opened, just close it
* out now */
get_session(s);
__unregister_session(mdsc, s);
__wake_requests(mdsc, &s->s_waiting);
ceph_put_mds_session(s);
} else if (i >= newmap->m_num_mds) {
/* force close session for stopped mds */
get_session(s);
__unregister_session(mdsc, s);
__wake_requests(mdsc, &s->s_waiting);
kick_requests(mdsc, i);
mutex_unlock(&mdsc->mutex);
mutex_lock(&s->s_mutex);
cleanup_session_requests(mdsc, s);
remove_session_caps(s);
mutex_unlock(&s->s_mutex);
ceph_put_mds_session(s);
mutex_lock(&mdsc->mutex);
} else {
/* just close it */
mutex_unlock(&mdsc->mutex);
mutex_lock(&s->s_mutex);
mutex_lock(&mdsc->mutex);
ceph_con_close(&s->s_con);
mutex_unlock(&s->s_mutex);
s->s_state = CEPH_MDS_SESSION_RESTARTING;
}
/* just close it */
mutex_unlock(&mdsc->mutex);
mutex_lock(&s->s_mutex);
mutex_lock(&mdsc->mutex);
ceph_con_close(&s->s_con);
mutex_unlock(&s->s_mutex);
s->s_state = CEPH_MDS_SESSION_RESTARTING;
} else if (oldstate == newstate) {
continue; /* nothing new with this mds */
}
@ -3931,31 +3940,33 @@ bad:
}
void ceph_mdsc_lease_send_msg(struct ceph_mds_session *session,
struct inode *inode,
struct dentry *dentry, char action,
u32 seq)
{
struct ceph_msg *msg;
struct ceph_mds_lease *lease;
int len = sizeof(*lease) + sizeof(u32);
int dnamelen = 0;
struct inode *dir;
int len = sizeof(*lease) + sizeof(u32) + NAME_MAX;
dout("lease_send_msg inode %p dentry %p %s to mds%d\n",
inode, dentry, ceph_lease_op_name(action), session->s_mds);
dnamelen = dentry->d_name.len;
len += dnamelen;
dout("lease_send_msg identry %p %s to mds%d\n",
dentry, ceph_lease_op_name(action), session->s_mds);
msg = ceph_msg_new(CEPH_MSG_CLIENT_LEASE, len, GFP_NOFS, false);
if (!msg)
return;
lease = msg->front.iov_base;
lease->action = action;
lease->ino = cpu_to_le64(ceph_vino(inode).ino);
lease->first = lease->last = cpu_to_le64(ceph_vino(inode).snap);
lease->seq = cpu_to_le32(seq);
put_unaligned_le32(dnamelen, lease + 1);
memcpy((void *)(lease + 1) + 4, dentry->d_name.name, dnamelen);
spin_lock(&dentry->d_lock);
dir = d_inode(dentry->d_parent);
lease->ino = cpu_to_le64(ceph_ino(dir));
lease->first = lease->last = cpu_to_le64(ceph_snap(dir));
put_unaligned_le32(dentry->d_name.len, lease + 1);
memcpy((void *)(lease + 1) + 4,
dentry->d_name.name, dentry->d_name.len);
spin_unlock(&dentry->d_lock);
/*
* if this is a preemptive lease RELEASE, no need to
* flush request stream, since the actual request will
@ -4157,6 +4168,7 @@ static void wait_requests(struct ceph_mds_client *mdsc)
while ((req = __get_oldest_req(mdsc))) {
dout("wait_requests timed out on tid %llu\n",
req->r_tid);
list_del_init(&req->r_wait);
__unregister_request(mdsc, req);
}
}

4
fs/ceph/mds_client.h
View File

@ -69,6 +69,9 @@ struct ceph_mds_reply_info_in {
u64 max_bytes;
u64 max_files;
s32 dir_pin;
struct ceph_timespec btime;
struct ceph_timespec snap_btime;
u64 change_attr;
};
struct ceph_mds_reply_dir_entry {
@ -504,7 +507,6 @@ extern char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base,
extern void __ceph_mdsc_drop_dentry_lease(struct dentry *dentry);
extern void ceph_mdsc_lease_send_msg(struct ceph_mds_session *session,
struct inode *inode,
struct dentry *dentry, char action,
u32 seq);

12
fs/ceph/mdsmap.c
View File

@ -107,7 +107,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
struct ceph_mdsmap *m;
const void *start = *p;
int i, j, n;
int err = -EINVAL;
int err;
u8 mdsmap_v, mdsmap_cv;
u16 mdsmap_ev;
@ -183,8 +183,9 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
inc = ceph_decode_32(p);
state = ceph_decode_32(p);
state_seq = ceph_decode_64(p);
ceph_decode_copy(p, &addr, sizeof(addr));
ceph_decode_addr(&addr);
err = ceph_decode_entity_addr(p, end, &addr);
if (err)
goto corrupt;
ceph_decode_copy(p, &laggy_since, sizeof(laggy_since));
*p += sizeof(u32);
ceph_decode_32_safe(p, end, namelen, bad);
@ -357,7 +358,7 @@ bad_ext:
nomem:
err = -ENOMEM;
goto out_err;
bad:
corrupt:
pr_err("corrupt mdsmap\n");
print_hex_dump(KERN_DEBUG, "mdsmap: ",
DUMP_PREFIX_OFFSET, 16, 1,
@ -365,6 +366,9 @@ bad:
out_err:
ceph_mdsmap_destroy(m);
return ERR_PTR(err);
bad:
err = -EINVAL;
goto corrupt;
}
void ceph_mdsmap_destroy(struct ceph_mdsmap *m)

15
fs/ceph/quota.c
View File

@ -135,7 +135,7 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc,
return NULL;
mutex_lock(&qri->mutex);
if (qri->inode) {
if (qri->inode && ceph_is_any_caps(qri->inode)) {
/* A request has already returned the inode */
mutex_unlock(&qri->mutex);
return qri->inode;
@ -146,7 +146,18 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc,
mutex_unlock(&qri->mutex);
return NULL;
}
in = ceph_lookup_inode(sb, realm->ino);
if (qri->inode) {
/* get caps */
int ret = __ceph_do_getattr(qri->inode, NULL,
CEPH_STAT_CAP_INODE, true);
if (ret >= 0)
in = qri->inode;
else
in = ERR_PTR(ret);
} else {
in = ceph_lookup_inode(sb, realm->ino);
}
if (IS_ERR(in)) {
pr_warn("Can't lookup inode %llx (err: %ld)\n",
realm->ino, PTR_ERR(in));

3
fs/ceph/snap.c
View File

@ -3,6 +3,7 @@
#include <linux/sort.h>
#include <linux/slab.h>
#include <linux/iversion.h>
#include "super.h"
#include "mds_client.h"
#include <linux/ceph/decode.h>
@ -606,6 +607,8 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
capsnap->mtime = inode->i_mtime;
capsnap->atime = inode->i_atime;
capsnap->ctime = inode->i_ctime;
capsnap->btime = ci->i_btime;
capsnap->change_attr = inode_peek_iversion_raw(inode);
capsnap->time_warp_seq = ci->i_time_warp_seq;
capsnap->truncate_size = ci->i_truncate_size;
capsnap->truncate_seq = ci->i_truncate_seq;

13
fs/ceph/super.c
View File

@ -840,10 +840,10 @@ static int ceph_remount(struct super_block *sb, int *flags, char *data)
static const struct super_operations ceph_super_ops = {
.alloc_inode = ceph_alloc_inode,
.destroy_inode = ceph_destroy_inode,
.free_inode = ceph_free_inode,
.write_inode = ceph_write_inode,
.drop_inode = ceph_drop_inode,
.drop_inode = generic_delete_inode,
.evict_inode = ceph_evict_inode,
.sync_fs = ceph_sync_fs,
.put_super = ceph_put_super,
.remount_fs = ceph_remount,
@ -978,7 +978,7 @@ static int ceph_set_super(struct super_block *s, void *data)
s->s_d_op = &ceph_dentry_ops;
s->s_export_op = &ceph_export_ops;
s->s_time_gran = 1000; /* 1000 ns == 1 us */
s->s_time_gran = 1;
ret = set_anon_super(s, NULL); /* what is that second arg for? */
if (ret != 0)
@ -1159,17 +1159,15 @@ static int __init init_ceph(void)
goto out;
ceph_flock_init();
ceph_xattr_init();
ret = register_filesystem(&ceph_fs_type);
if (ret)
goto out_xattr;
goto out_caches;
pr_info("loaded (mds proto %d)\n", CEPH_MDSC_PROTOCOL);
return 0;
out_xattr:
ceph_xattr_exit();
out_caches:
destroy_caches();
out:
return ret;
@ -1179,7 +1177,6 @@ static void __exit exit_ceph(void)
{
dout("exit_ceph\n");
unregister_filesystem(&ceph_fs_type);
ceph_xattr_exit();
destroy_caches();
}

67
fs/ceph/super.h
View File

@ -197,7 +197,8 @@ struct ceph_cap_snap {
u64 xattr_version;
u64 size;
struct timespec64 mtime, atime, ctime;
u64 change_attr;
struct timespec64 mtime, atime, ctime, btime;
u64 time_warp_seq;
u64 truncate_size;
u32 truncate_seq;
@ -384,6 +385,8 @@ struct ceph_inode_info {
int i_snap_realm_counter; /* snap realm (if caps) */
struct list_head i_snap_realm_item;
struct list_head i_snap_flush_item;
struct timespec64 i_btime;
struct timespec64 i_snap_btime;
struct work_struct i_work;
unsigned long i_work_mask;
@ -544,7 +547,12 @@ static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
long long release_count,
long long ordered_count)
{
smp_mb__before_atomic();
/*
* Makes sure operations that setup readdir cache (update page
* cache and i_size) are strongly ordered w.r.t. the following
* atomic64_set() operations.
*/
smp_mb();
atomic64_set(&ci->i_complete_seq[0], release_count);
atomic64_set(&ci->i_complete_seq[1], ordered_count);
}
@ -876,9 +884,8 @@ static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci)
extern const struct inode_operations ceph_file_iops;
extern struct inode *ceph_alloc_inode(struct super_block *sb);
extern void ceph_destroy_inode(struct inode *inode);
extern void ceph_evict_inode(struct inode *inode);
extern void ceph_free_inode(struct inode *inode);
extern int ceph_drop_inode(struct inode *inode);
extern struct inode *ceph_get_inode(struct super_block *sb,
struct ceph_vino vino);
@ -921,10 +928,20 @@ ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t);
extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci);
extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
extern void __init ceph_xattr_init(void);
extern void ceph_xattr_exit(void);
extern const struct xattr_handler *ceph_xattr_handlers[];
struct ceph_acl_sec_ctx {
#ifdef CONFIG_CEPH_FS_POSIX_ACL
void *default_acl;
void *acl;
#endif
#ifdef CONFIG_CEPH_FS_SECURITY_LABEL
void *sec_ctx;
u32 sec_ctxlen;
#endif
struct ceph_pagelist *pagelist;
};
#ifdef CONFIG_SECURITY
extern bool ceph_security_xattr_deadlock(struct inode *in);
extern bool ceph_security_xattr_wanted(struct inode *in);
@ -939,21 +956,32 @@ static inline bool ceph_security_xattr_wanted(struct inode *in)
}
#endif
/* acl.c */
struct ceph_acls_info {
void *default_acl;
void *acl;
struct ceph_pagelist *pagelist;
};
#ifdef CONFIG_CEPH_FS_SECURITY_LABEL
extern int ceph_security_init_secctx(struct dentry *dentry, umode_t mode,
struct ceph_acl_sec_ctx *ctx);
extern void ceph_security_invalidate_secctx(struct inode *inode);
#else
static inline int ceph_security_init_secctx(struct dentry *dentry, umode_t mode,
struct ceph_acl_sec_ctx *ctx)
{
return 0;
}
static inline void ceph_security_invalidate_secctx(struct inode *inode)
{
}
#endif
void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx);
/* acl.c */
#ifdef CONFIG_CEPH_FS_POSIX_ACL
struct posix_acl *ceph_get_acl(struct inode *, int);
int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type);
int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
struct ceph_acls_info *info);
void ceph_init_inode_acls(struct inode *inode, struct ceph_acls_info *info);
void ceph_release_acls_info(struct ceph_acls_info *info);
struct ceph_acl_sec_ctx *as_ctx);
void ceph_init_inode_acls(struct inode *inode,
struct ceph_acl_sec_ctx *as_ctx);
static inline void ceph_forget_all_cached_acls(struct inode *inode)
{
@ -966,15 +994,12 @@ static inline void ceph_forget_all_cached_acls(struct inode *inode)
#define ceph_set_acl NULL
static inline int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
struct ceph_acls_info *info)
struct ceph_acl_sec_ctx *as_ctx)
{
return 0;
}
static inline void ceph_init_inode_acls(struct inode *inode,
struct ceph_acls_info *info)
{
}
static inline void ceph_release_acls_info(struct ceph_acls_info *info)
struct ceph_acl_sec_ctx *as_ctx)
{
}
static inline int ceph_acl_chmod(struct dentry *dentry, struct inode *inode)
@ -1000,7 +1025,7 @@ extern void ceph_add_cap(struct inode *inode,
unsigned cap, unsigned seq, u64 realmino, int flags,
struct ceph_cap **new_cap);
extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
extern void __ceph_remove_caps(struct inode* inode);
extern void __ceph_remove_caps(struct ceph_inode_info *ci);
extern void ceph_put_cap(struct ceph_mds_client *mdsc,
struct ceph_cap *cap);
extern int ceph_is_any_caps(struct inode *inode);

496
fs/ceph/xattr.c
View File

@ -8,6 +8,7 @@
#include <linux/ceph/decode.h>
#include <linux/xattr.h>
#include <linux/security.h>
#include <linux/posix_acl_xattr.h>
#include <linux/slab.h>
@ -17,26 +18,9 @@
static int __remove_xattr(struct ceph_inode_info *ci,
struct ceph_inode_xattr *xattr);
static const struct xattr_handler ceph_other_xattr_handler;
/*
* List of handlers for synthetic system.* attributes. Other
* attributes are handled directly.
*/
const struct xattr_handler *ceph_xattr_handlers[] = {
#ifdef CONFIG_CEPH_FS_POSIX_ACL
&posix_acl_access_xattr_handler,
&posix_acl_default_xattr_handler,
#endif
&ceph_other_xattr_handler,
NULL,
};
static bool ceph_is_valid_xattr(const char *name)
{
return !strncmp(name, XATTR_CEPH_PREFIX, XATTR_CEPH_PREFIX_LEN) ||
!strncmp(name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN) ||
!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN);
}
@ -48,8 +32,8 @@ static bool ceph_is_valid_xattr(const char *name)
struct ceph_vxattr {
char *name;
size_t name_size; /* strlen(name) + 1 (for '\0') */
size_t (*getxattr_cb)(struct ceph_inode_info *ci, char *val,
size_t size);
ssize_t (*getxattr_cb)(struct ceph_inode_info *ci, char *val,
size_t size);
bool (*exists_cb)(struct ceph_inode_info *ci);
unsigned int flags;
};
@ -68,8 +52,8 @@ static bool ceph_vxattrcb_layout_exists(struct ceph_inode_info *ci)
rcu_dereference_raw(fl->pool_ns) != NULL);
}
static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
size_t size)
static ssize_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
size_t size)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
struct ceph_osd_client *osdc = &fsc->client->osdc;
@ -79,7 +63,7 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
const char *ns_field = " pool_namespace=";
char buf[128];
size_t len, total_len = 0;
int ret;
ssize_t ret;
pool_ns = ceph_try_get_string(ci->i_layout.pool_ns);
@ -96,18 +80,15 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
len = snprintf(buf, sizeof(buf),
"stripe_unit=%u stripe_count=%u object_size=%u pool=%lld",
ci->i_layout.stripe_unit, ci->i_layout.stripe_count,
ci->i_layout.object_size, (unsigned long long)pool);
ci->i_layout.object_size, pool);
total_len = len;
}
if (pool_ns)
total_len += strlen(ns_field) + pool_ns->len;
if (!size) {
ret = total_len;
} else if (total_len > size) {
ret = -ERANGE;
} else {
ret = total_len;
if (size >= total_len) {
memcpy(val, buf, len);
ret = len;
if (pool_name) {
@ -128,28 +109,55 @@ static size_t ceph_vxattrcb_layout(struct ceph_inode_info *ci, char *val,
return ret;
}
static size_t ceph_vxattrcb_layout_stripe_unit(struct ceph_inode_info *ci,
char *val, size_t size)
{
return snprintf(val, size, "%u", ci->i_layout.stripe_unit);
}
static size_t ceph_vxattrcb_layout_stripe_count(struct ceph_inode_info *ci,
char *val, size_t size)
{
return snprintf(val, size, "%u", ci->i_layout.stripe_count);
}
static size_t ceph_vxattrcb_layout_object_size(struct ceph_inode_info *ci,
char *val, size_t size)
{
return snprintf(val, size, "%u", ci->i_layout.object_size);
}
static size_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci,
char *val, size_t size)
/*
* The convention with strings in xattrs is that they should not be NULL
* terminated, since we're returning the length with them. snprintf always
* NULL terminates however, so call it on a temporary buffer and then memcpy
* the result into place.
*/
static int ceph_fmt_xattr(char *val, size_t size, const char *fmt, ...)
{
int ret;
va_list args;
char buf[96]; /* NB: reevaluate size if new vxattrs are added */
va_start(args, fmt);
ret = vsnprintf(buf, size ? sizeof(buf) : 0, fmt, args);
va_end(args);
/* Sanity check */
if (size && ret + 1 > sizeof(buf)) {
WARN_ONCE(true, "Returned length too big (%d)", ret);
return -E2BIG;
}
if (ret <= size)
memcpy(val, buf, ret);
return ret;
}
static ssize_t ceph_vxattrcb_layout_stripe_unit(struct ceph_inode_info *ci,
char *val, size_t size)
{
return ceph_fmt_xattr(val, size, "%u", ci->i_layout.stripe_unit);
}
static ssize_t ceph_vxattrcb_layout_stripe_count(struct ceph_inode_info *ci,
char *val, size_t size)
{
return ceph_fmt_xattr(val, size, "%u", ci->i_layout.stripe_count);
}
static ssize_t ceph_vxattrcb_layout_object_size(struct ceph_inode_info *ci,
char *val, size_t size)
{
return ceph_fmt_xattr(val, size, "%u", ci->i_layout.object_size);
}
static ssize_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci,
char *val, size_t size)
{
ssize_t ret;
struct ceph_fs_client *fsc = ceph_sb_to_client(ci->vfs_inode.i_sb);
struct ceph_osd_client *osdc = &fsc->client->osdc;
s64 pool = ci->i_layout.pool_id;
@ -157,21 +165,27 @@ static size_t ceph_vxattrcb_layout_pool(struct ceph_inode_info *ci,
down_read(&osdc->lock);
pool_name = ceph_pg_pool_name_by_id(osdc->osdmap, pool);
if (pool_name)
ret = snprintf(val, size, "%s", pool_name);
else
ret = snprintf(val, size, "%lld", (unsigned long long)pool);
if (pool_name) {
ret = strlen(pool_name);
if (ret <= size)
memcpy(val, pool_name, ret);
} else {
ret = ceph_fmt_xattr(val, size, "%lld", pool);
}
up_read(&osdc->lock);
return ret;
}
static size_t ceph_vxattrcb_layout_pool_namespace(struct ceph_inode_info *ci,
char *val, size_t size)
static ssize_t ceph_vxattrcb_layout_pool_namespace(struct ceph_inode_info *ci,
char *val, size_t size)
{
int ret = 0;
ssize_t ret = 0;
struct ceph_string *ns = ceph_try_get_string(ci->i_layout.pool_ns);
if (ns) {
ret = snprintf(val, size, "%.*s", (int)ns->len, ns->str);
ret = ns->len;
if (ret <= size)
memcpy(val, ns->str, ret);
ceph_put_string(ns);
}
return ret;
@ -179,53 +193,54 @@ static size_t ceph_vxattrcb_layout_pool_namespace(struct ceph_inode_info *ci,
/* directories */
static size_t ceph_vxattrcb_dir_entries(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_files + ci->i_subdirs);
}
static size_t ceph_vxattrcb_dir_files(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_files);
}
static size_t ceph_vxattrcb_dir_subdirs(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_subdirs);
}
static size_t ceph_vxattrcb_dir_rentries(struct ceph_inode_info *ci, char *val,
static ssize_t ceph_vxattrcb_dir_entries(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_rfiles + ci->i_rsubdirs);
return ceph_fmt_xattr(val, size, "%lld", ci->i_files + ci->i_subdirs);
}
static size_t ceph_vxattrcb_dir_rfiles(struct ceph_inode_info *ci, char *val,
static ssize_t ceph_vxattrcb_dir_files(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_rfiles);
return ceph_fmt_xattr(val, size, "%lld", ci->i_files);
}
static size_t ceph_vxattrcb_dir_rsubdirs(struct ceph_inode_info *ci, char *val,
static ssize_t ceph_vxattrcb_dir_subdirs(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_rsubdirs);
return ceph_fmt_xattr(val, size, "%lld", ci->i_subdirs);
}
static size_t ceph_vxattrcb_dir_rbytes(struct ceph_inode_info *ci, char *val,
size_t size)
static ssize_t ceph_vxattrcb_dir_rentries(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld", ci->i_rbytes);
return ceph_fmt_xattr(val, size, "%lld",
ci->i_rfiles + ci->i_rsubdirs);
}
static size_t ceph_vxattrcb_dir_rctime(struct ceph_inode_info *ci, char *val,
size_t size)
static ssize_t ceph_vxattrcb_dir_rfiles(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%lld.09%ld", ci->i_rctime.tv_sec,
ci->i_rctime.tv_nsec);
return ceph_fmt_xattr(val, size, "%lld", ci->i_rfiles);
}
static ssize_t ceph_vxattrcb_dir_rsubdirs(struct ceph_inode_info *ci, char *val,
size_t size)
{
return ceph_fmt_xattr(val, size, "%lld", ci->i_rsubdirs);
}
static ssize_t ceph_vxattrcb_dir_rbytes(struct ceph_inode_info *ci, char *val,
size_t size)
{
return ceph_fmt_xattr(val, size, "%lld", ci->i_rbytes);
}
static ssize_t ceph_vxattrcb_dir_rctime(struct ceph_inode_info *ci, char *val,
size_t size)
{
return ceph_fmt_xattr(val, size, "%lld.%09ld", ci->i_rctime.tv_sec,
ci->i_rctime.tv_nsec);
}
/* dir pin */
@ -234,10 +249,10 @@ static bool ceph_vxattrcb_dir_pin_exists(struct ceph_inode_info *ci)
return ci->i_dir_pin != -ENODATA;
}
static size_t ceph_vxattrcb_dir_pin(struct ceph_inode_info *ci, char *val,
size_t size)
static ssize_t ceph_vxattrcb_dir_pin(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "%d", (int)ci->i_dir_pin);
return ceph_fmt_xattr(val, size, "%d", (int)ci->i_dir_pin);
}
/* quotas */
@ -254,23 +269,36 @@ static bool ceph_vxattrcb_quota_exists(struct ceph_inode_info *ci)
return ret;
}
static size_t ceph_vxattrcb_quota(struct ceph_inode_info *ci, char *val,
size_t size)
static ssize_t ceph_vxattrcb_quota(struct ceph_inode_info *ci, char *val,
size_t size)
{
return snprintf(val, size, "max_bytes=%llu max_files=%llu",
ci->i_max_bytes, ci->i_max_files);
return ceph_fmt_xattr(val, size, "max_bytes=%llu max_files=%llu",
ci->i_max_bytes, ci->i_max_files);
}
static size_t ceph_vxattrcb_quota_max_bytes(struct ceph_inode_info *ci,
char *val, size_t size)
static ssize_t ceph_vxattrcb_quota_max_bytes(struct ceph_inode_info *ci,
char *val, size_t size)
{
return snprintf(val, size, "%llu", ci->i_max_bytes);
return ceph_fmt_xattr(val, size, "%llu", ci->i_max_bytes);
}
static size_t ceph_vxattrcb_quota_max_files(struct ceph_inode_info *ci,
char *val, size_t size)
static ssize_t ceph_vxattrcb_quota_max_files(struct ceph_inode_info *ci,
char *val, size_t size)
{
return snprintf(val, size, "%llu", ci->i_max_files);
return ceph_fmt_xattr(val, size, "%llu", ci->i_max_files);
}
/* snapshots */
static bool ceph_vxattrcb_snap_btime_exists(struct ceph_inode_info *ci)
{
return (ci->i_snap_btime.tv_sec != 0 || ci->i_snap_btime.tv_nsec != 0);
}
static ssize_t ceph_vxattrcb_snap_btime(struct ceph_inode_info *ci, char *val,
size_t size)
{
return ceph_fmt_xattr(val, size, "%lld.%09ld", ci->i_snap_btime.tv_sec,
ci->i_snap_btime.tv_nsec);
}
#define CEPH_XATTR_NAME(_type, _name) XATTR_CEPH_PREFIX #_type "." #_name
@ -327,7 +355,7 @@ static struct ceph_vxattr ceph_dir_vxattrs[] = {
XATTR_RSTAT_FIELD(dir, rctime),
{
.name = "ceph.dir.pin",
.name_size = sizeof("ceph.dir_pin"),
.name_size = sizeof("ceph.dir.pin"),
.getxattr_cb = ceph_vxattrcb_dir_pin,
.exists_cb = ceph_vxattrcb_dir_pin_exists,
.flags = VXATTR_FLAG_HIDDEN,
@ -341,9 +369,15 @@ static struct ceph_vxattr ceph_dir_vxattrs[] = {
},
XATTR_QUOTA_FIELD(quota, max_bytes),
XATTR_QUOTA_FIELD(quota, max_files),
{
.name = "ceph.snap.btime",
.name_size = sizeof("ceph.snap.btime"),
.getxattr_cb = ceph_vxattrcb_snap_btime,
.exists_cb = ceph_vxattrcb_snap_btime_exists,
.flags = VXATTR_FLAG_READONLY,
},
{ .name = NULL, 0 } /* Required table terminator */
};
static size_t ceph_dir_vxattrs_name_size; /* total size of all names */
/* files */
@ -360,9 +394,15 @@ static struct ceph_vxattr ceph_file_vxattrs[] = {
XATTR_LAYOUT_FIELD(file, layout, object_size),
XATTR_LAYOUT_FIELD(file, layout, pool),
XATTR_LAYOUT_FIELD(file, layout, pool_namespace),
{
.name = "ceph.snap.btime",
.name_size = sizeof("ceph.snap.btime"),
.getxattr_cb = ceph_vxattrcb_snap_btime,
.exists_cb = ceph_vxattrcb_snap_btime_exists,
.flags = VXATTR_FLAG_READONLY,
},
{ .name = NULL, 0 } /* Required table terminator */
};
static size_t ceph_file_vxattrs_name_size; /* total size of all names */
static struct ceph_vxattr *ceph_inode_vxattrs(struct inode *inode)
{
@ -373,47 +413,6 @@ static struct ceph_vxattr *ceph_inode_vxattrs(struct inode *inode)
return NULL;
}
static size_t ceph_vxattrs_name_size(struct ceph_vxattr *vxattrs)
{
if (vxattrs == ceph_dir_vxattrs)
return ceph_dir_vxattrs_name_size;
if (vxattrs == ceph_file_vxattrs)
return ceph_file_vxattrs_name_size;
BUG_ON(vxattrs);
return 0;
}
/*
* Compute the aggregate size (including terminating '\0') of all
* virtual extended attribute names in the given vxattr table.
*/
static size_t __init vxattrs_name_size(struct ceph_vxattr *vxattrs)
{
struct ceph_vxattr *vxattr;
size_t size = 0;
for (vxattr = vxattrs; vxattr->name; vxattr++) {
if (!(vxattr->flags & VXATTR_FLAG_HIDDEN))
size += vxattr->name_size;
}
return size;
}
/* Routines called at initialization and exit time */
void __init ceph_xattr_init(void)
{
ceph_dir_vxattrs_name_size = vxattrs_name_size(ceph_dir_vxattrs);
ceph_file_vxattrs_name_size = vxattrs_name_size(ceph_file_vxattrs);
}
void ceph_xattr_exit(void)
{
ceph_dir_vxattrs_name_size = 0;
ceph_file_vxattrs_name_size = 0;
}
static struct ceph_vxattr *ceph_match_vxattr(struct inode *inode,
const char *name)
{
@ -523,8 +522,8 @@ static int __set_xattr(struct ceph_inode_info *ci,
dout("__set_xattr_val p=%p\n", p);
}
dout("__set_xattr_val added %llx.%llx xattr %p %s=%.*s\n",
ceph_vinop(&ci->vfs_inode), xattr, name, val_len, val);
dout("__set_xattr_val added %llx.%llx xattr %p %.*s=%.*s\n",
ceph_vinop(&ci->vfs_inode), xattr, name_len, name, val_len, val);
return 0;
}
@ -823,7 +822,7 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
struct ceph_inode_xattr *xattr;
struct ceph_vxattr *vxattr = NULL;
int req_mask;
int err;
ssize_t err;
/* let's see if a virtual xattr was requested */
vxattr = ceph_match_vxattr(inode, name);
@ -835,8 +834,11 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
if (err)
return err;
err = -ENODATA;
if (!(vxattr->exists_cb && !vxattr->exists_cb(ci)))
if (!(vxattr->exists_cb && !vxattr->exists_cb(ci))) {
err = vxattr->getxattr_cb(ci, value, size);
if (size && size < err)
err = -ERANGE;
}
return err;
}
@ -897,10 +899,9 @@ ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
struct inode *inode = d_inode(dentry);
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_vxattr *vxattrs = ceph_inode_vxattrs(inode);
u32 vir_namelen = 0;
bool len_only = (size == 0);
u32 namelen;
int err;
u32 len;
int i;
spin_lock(&ci->i_ceph_lock);
@ -919,38 +920,45 @@ ssize_t ceph_listxattr(struct dentry *dentry, char *names, size_t size)
err = __build_xattrs(inode);
if (err < 0)
goto out;
/*
* Start with virtual dir xattr names (if any) (including
* terminating '\0' characters for each).
*/
vir_namelen = ceph_vxattrs_name_size(vxattrs);
/* adding 1 byte per each variable due to the null termination */
/* add 1 byte for each xattr due to the null termination */
namelen = ci->i_xattrs.names_size + ci->i_xattrs.count;
err = -ERANGE;
if (size && vir_namelen + namelen > size)
goto out;
err = namelen + vir_namelen;
if (size == 0)
goto out;
names = __copy_xattr_names(ci, names);
/* virtual xattr names, too */
err = namelen;
if (vxattrs) {
for (i = 0; vxattrs[i].name; i++) {
if (!(vxattrs[i].flags & VXATTR_FLAG_HIDDEN) &&
!(vxattrs[i].exists_cb &&
!vxattrs[i].exists_cb(ci))) {
len = sprintf(names, "%s", vxattrs[i].name);
names += len + 1;
err += len + 1;
}
if (!len_only) {
if (namelen > size) {
err = -ERANGE;
goto out;
}
names = __copy_xattr_names(ci, names);
size -= namelen;
}
/* virtual xattr names, too */
if (vxattrs) {
for (i = 0; vxattrs[i].name; i++) {
size_t this_len;
if (vxattrs[i].flags & VXATTR_FLAG_HIDDEN)
continue;
if (vxattrs[i].exists_cb && !vxattrs[i].exists_cb(ci))
continue;
this_len = strlen(vxattrs[i].name) + 1;
namelen += this_len;
if (len_only)
continue;
if (this_len > size) {
err = -ERANGE;
goto out;
}
memcpy(names, vxattrs[i].name, this_len);
names += this_len;
size -= this_len;
}
}
err = namelen;
out:
spin_unlock(&ci->i_ceph_lock);
return err;
@ -1206,4 +1214,138 @@ bool ceph_security_xattr_deadlock(struct inode *in)
spin_unlock(&ci->i_ceph_lock);
return ret;
}
#ifdef CONFIG_CEPH_FS_SECURITY_LABEL
int ceph_security_init_secctx(struct dentry *dentry, umode_t mode,
struct ceph_acl_sec_ctx *as_ctx)
{
struct ceph_pagelist *pagelist = as_ctx->pagelist;
const char *name;
size_t name_len;
int err;
err = security_dentry_init_security(dentry, mode, &dentry->d_name,
&as_ctx->sec_ctx,
&as_ctx->sec_ctxlen);
if (err < 0) {
WARN_ON_ONCE(err != -EOPNOTSUPP);
err = 0; /* do nothing */
goto out;
}
err = -ENOMEM;
if (!pagelist) {
pagelist = ceph_pagelist_alloc(GFP_KERNEL);
if (!pagelist)
goto out;
err = ceph_pagelist_reserve(pagelist, PAGE_SIZE);
if (err)
goto out;
ceph_pagelist_encode_32(pagelist, 1);
}
/*
* FIXME: Make security_dentry_init_security() generic. Currently
* It only supports single security module and only selinux has
* dentry_init_security hook.
*/
name = XATTR_NAME_SELINUX;
name_len = strlen(name);
err = ceph_pagelist_reserve(pagelist,
4 * 2 + name_len + as_ctx->sec_ctxlen);
if (err)
goto out;
if (as_ctx->pagelist) {
/* update count of KV pairs */
BUG_ON(pagelist->length <= sizeof(__le32));
if (list_is_singular(&pagelist->head)) {
le32_add_cpu((__le32*)pagelist->mapped_tail, 1);
} else {
struct page *page = list_first_entry(&pagelist->head,
struct page, lru);
void *addr = kmap_atomic(page);
le32_add_cpu((__le32*)addr, 1);
kunmap_atomic(addr);
}
} else {
as_ctx->pagelist = pagelist;
}
ceph_pagelist_encode_32(pagelist, name_len);
ceph_pagelist_append(pagelist, name, name_len);
ceph_pagelist_encode_32(pagelist, as_ctx->sec_ctxlen);
ceph_pagelist_append(pagelist, as_ctx->sec_ctx, as_ctx->sec_ctxlen);
err = 0;
out:
if (pagelist && !as_ctx->pagelist)
ceph_pagelist_release(pagelist);
return err;
}
void ceph_security_invalidate_secctx(struct inode *inode)
{
security_inode_invalidate_secctx(inode);
}
static int ceph_xattr_set_security_label(const struct xattr_handler *handler,
struct dentry *unused, struct inode *inode,
const char *key, const void *buf,
size_t buflen, int flags)
{
if (security_ismaclabel(key)) {
const char *name = xattr_full_name(handler, key);
return __ceph_setxattr(inode, name, buf, buflen, flags);
}
return -EOPNOTSUPP;
}
static int ceph_xattr_get_security_label(const struct xattr_handler *handler,
struct dentry *unused, struct inode *inode,
const char *key, void *buf, size_t buflen)
{
if (security_ismaclabel(key)) {
const char *name = xattr_full_name(handler, key);
return __ceph_getxattr(inode, name, buf, buflen);
}
return -EOPNOTSUPP;
}
static const struct xattr_handler ceph_security_label_handler = {
.prefix = XATTR_SECURITY_PREFIX,
.get = ceph_xattr_get_security_label,
.set = ceph_xattr_set_security_label,
};
#endif
#endif
void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx)
{
#ifdef CONFIG_CEPH_FS_POSIX_ACL
posix_acl_release(as_ctx->acl);
posix_acl_release(as_ctx->default_acl);
#endif
#ifdef CONFIG_CEPH_FS_SECURITY_LABEL
security_release_secctx(as_ctx->sec_ctx, as_ctx->sec_ctxlen);
#endif
if (as_ctx->pagelist)
ceph_pagelist_release(as_ctx->pagelist);
}
/*
* List of handlers for synthetic system.* attributes. Other
* attributes are handled directly.
*/
const struct xattr_handler *ceph_xattr_handlers[] = {
#ifdef CONFIG_CEPH_FS_POSIX_ACL
&posix_acl_access_xattr_handler,
&posix_acl_default_xattr_handler,
#endif
#ifdef CONFIG_CEPH_FS_SECURITY_LABEL
&ceph_security_label_handler,
#endif
&ceph_other_xattr_handler,
NULL,
};

1
include/linux/ceph/ceph_features.h
View File

@ -211,6 +211,7 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin
CEPH_FEATURE_MON_STATEFUL_SUB | \
CEPH_FEATURE_CRUSH_TUNABLES5 | \
CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING | \
CEPH_FEATURE_MSG_ADDR2 | \
CEPH_FEATURE_CEPHX_V2)
#define CEPH_FEATURES_REQUIRED_DEFAULT 0

2
include/linux/ceph/ceph_fs.h
View File

@ -682,7 +682,7 @@ extern const char *ceph_cap_op_name(int op);
/* flags field in client cap messages (version >= 10) */
#define CEPH_CLIENT_CAPS_SYNC (1<<0)
#define CEPH_CLIENT_CAPS_NO_CAPSNAP (1<<1)
#define CEPH_CLIENT_CAPS_PENDING_CAPSNAP (1<<2);
#define CEPH_CLIENT_CAPS_PENDING_CAPSNAP (1<<2)
/*
* caps message, used for capability callbacks, acks, requests, etc.

3
include/linux/ceph/cls_lock_client.h
View File

@ -52,4 +52,7 @@ int ceph_cls_lock_info(struct ceph_osd_client *osdc,
char *lock_name, u8 *type, char **tag,
struct ceph_locker **lockers, u32 *num_lockers);
int ceph_cls_assert_locked(struct ceph_osd_request *req, int which,
char *lock_name, u8 type, char *cookie, char *tag);
#endif

13
include/linux/ceph/decode.h
View File

@ -218,18 +218,27 @@ static inline void ceph_encode_timespec64(struct ceph_timespec *tv,
/*
* sockaddr_storage <-> ceph_sockaddr
*/
static inline void ceph_encode_addr(struct ceph_entity_addr *a)
#define CEPH_ENTITY_ADDR_TYPE_NONE 0
#define CEPH_ENTITY_ADDR_TYPE_LEGACY __cpu_to_le32(1)
static inline void ceph_encode_banner_addr(struct ceph_entity_addr *a)
{
__be16 ss_family = htons(a->in_addr.ss_family);
a->in_addr.ss_family = *(__u16 *)&ss_family;
/* Banner addresses require TYPE_NONE */
a->type = CEPH_ENTITY_ADDR_TYPE_NONE;
}
static inline void ceph_decode_addr(struct ceph_entity_addr *a)
static inline void ceph_decode_banner_addr(struct ceph_entity_addr *a)
{
__be16 ss_family = *(__be16 *)&a->in_addr.ss_family;
a->in_addr.ss_family = ntohs(ss_family);
WARN_ON(a->in_addr.ss_family == 512);
a->type = CEPH_ENTITY_ADDR_TYPE_LEGACY;
}
extern int ceph_decode_entity_addr(void **p, void *end,
struct ceph_entity_addr *addr);
/*
* encoders
*/

10
include/linux/ceph/libceph.h
View File

@ -84,11 +84,13 @@ struct ceph_options {
#define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024)
/*
* Handle the largest possible rbd object in one message.
* The largest possible rbd data object is 32M.
* The largest possible rbd object map object is 64M.
*
* There is no limit on the size of cephfs objects, but it has to obey
* rsize and wsize mount options anyway.
*/
#define CEPH_MSG_MAX_DATA_LEN (32*1024*1024)
#define CEPH_MSG_MAX_DATA_LEN (64*1024*1024)
#define CEPH_AUTH_NAME_DEFAULT "guest"
@ -299,10 +301,6 @@ int ceph_wait_for_latest_osdmap(struct ceph_client *client,
/* pagevec.c */
extern void ceph_release_page_vector(struct page **pages, int num_pages);
extern struct page **ceph_get_direct_page_vector(const void __user *data,
int num_pages,
bool write_page);
extern void ceph_put_page_vector(struct page **pages, int num_pages,
bool dirty);
extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);

1
include/linux/ceph/mon_client.h
View File

@ -104,7 +104,6 @@ struct ceph_mon_client {
#endif
};
extern struct ceph_monmap *ceph_monmap_decode(void *p, void *end);
extern int ceph_monmap_contains(struct ceph_monmap *m,
struct ceph_entity_addr *addr);

12
include/linux/ceph/osd_client.h
View File

@ -198,9 +198,9 @@ struct ceph_osd_request {
bool r_mempool;
struct completion r_completion; /* private to osd_client.c */
ceph_osdc_callback_t r_callback;
struct list_head r_unsafe_item;
struct inode *r_inode; /* for use by callbacks */
struct list_head r_private_item; /* ditto */
void *r_priv; /* ditto */
/* set by submitter */
@ -389,6 +389,14 @@ extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb);
void ceph_osdc_abort_requests(struct ceph_osd_client *osdc, int err);
#define osd_req_op_data(oreq, whch, typ, fld) \
({ \
struct ceph_osd_request *__oreq = (oreq); \
unsigned int __whch = (whch); \
BUG_ON(__whch >= __oreq->r_num_ops); \
&__oreq->r_ops[__whch].typ.fld; \
})
extern void osd_req_op_init(struct ceph_osd_request *osd_req,
unsigned int which, u16 opcode, u32 flags);
@ -497,7 +505,7 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
const char *class, const char *method,
unsigned int flags,
struct page *req_page, size_t req_len,
struct page *resp_page, size_t *resp_len);
struct page **resp_pages, size_t *resp_len);
extern int ceph_osdc_readpages(struct ceph_osd_client *osdc,
struct ceph_vino vino,

2
include/linux/ceph/striper.h
View File

@ -66,4 +66,6 @@ int ceph_extent_to_file(struct ceph_file_layout *l,
struct ceph_file_extent **file_extents,
u32 *num_file_extents);
u64 ceph_get_num_objects(struct ceph_file_layout *l, u64 size);
#endif

24
include/linux/iversion.h
View File

@ -112,6 +112,30 @@ inode_peek_iversion_raw(const struct inode *inode)
return atomic64_read(&inode->i_version);
}
/**
* inode_set_max_iversion_raw - update i_version new value is larger
* @inode: inode to set
* @val: new i_version to set
*
* Some self-managed filesystems (e.g Ceph) will only update the i_version
* value if the new value is larger than the one we already have.
*/
static inline void
inode_set_max_iversion_raw(struct inode *inode, u64 val)
{
u64 cur, old;
cur = inode_peek_iversion_raw(inode);
for (;;) {
if (cur > val)
break;
old = atomic64_cmpxchg(&inode->i_version, cur, val);
if (likely(old == cur))
break;
cur = old;
}
}
/**
* inode_set_iversion - set i_version to a particular value
* @inode: inode to set

2
net/ceph/Makefile
View File

@ -5,7 +5,7 @@
obj-$(CONFIG_CEPH_LIB) += libceph.o
libceph-y := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \
mon_client.o \
mon_client.o decode.o \
cls_lock_client.o \
osd_client.o osdmap.o crush/crush.o crush/mapper.o crush/hash.o \
striper.o \

54
net/ceph/cls_lock_client.c
View File

@ -6,6 +6,7 @@
#include <linux/ceph/cls_lock_client.h>
#include <linux/ceph/decode.h>
#include <linux/ceph/libceph.h>
/**
* ceph_cls_lock - grab rados lock for object
@ -264,8 +265,11 @@ static int decode_locker(void **p, void *end, struct ceph_locker *locker)
return ret;
*p += sizeof(struct ceph_timespec); /* skip expiration */
ceph_decode_copy(p, &locker->info.addr, sizeof(locker->info.addr));
ceph_decode_addr(&locker->info.addr);
ret = ceph_decode_entity_addr(p, end, &locker->info.addr);
if (ret)
return ret;
len = ceph_decode_32(p);
*p += len; /* skip description */
@ -360,7 +364,7 @@ int ceph_cls_lock_info(struct ceph_osd_client *osdc,
dout("%s lock_name %s\n", __func__, lock_name);
ret = ceph_osdc_call(osdc, oid, oloc, "lock", "get_info",
CEPH_OSD_FLAG_READ, get_info_op_page,
get_info_op_buf_size, reply_page, &reply_len);
get_info_op_buf_size, &reply_page, &reply_len);
dout("%s: status %d\n", __func__, ret);
if (ret >= 0) {
@ -375,3 +379,47 @@ int ceph_cls_lock_info(struct ceph_osd_client *osdc,
return ret;
}
EXPORT_SYMBOL(ceph_cls_lock_info);
int ceph_cls_assert_locked(struct ceph_osd_request *req, int which,
char *lock_name, u8 type, char *cookie, char *tag)
{
int assert_op_buf_size;
int name_len = strlen(lock_name);
int cookie_len = strlen(cookie);
int tag_len = strlen(tag);
struct page **pages;
void *p, *end;
int ret;
assert_op_buf_size = name_len + sizeof(__le32) +
cookie_len + sizeof(__le32) +
tag_len + sizeof(__le32) +
sizeof(u8) + CEPH_ENCODING_START_BLK_LEN;
if (assert_op_buf_size > PAGE_SIZE)
return -E2BIG;
ret = osd_req_op_cls_init(req, which, "lock", "assert_locked");
if (ret)
return ret;
pages = ceph_alloc_page_vector(1, GFP_NOIO);
if (IS_ERR(pages))
return PTR_ERR(pages);
p = page_address(pages[0]);
end = p + assert_op_buf_size;
/* encode cls_lock_assert_op struct */
ceph_start_encoding(&p, 1, 1,
assert_op_buf_size - CEPH_ENCODING_START_BLK_LEN);
ceph_encode_string(&p, end, lock_name, name_len);
ceph_encode_8(&p, type);
ceph_encode_string(&p, end, cookie, cookie_len);
ceph_encode_string(&p, end, tag, tag_len);
WARN_ON(p != end);
osd_req_op_cls_request_data_pages(req, which, pages, assert_op_buf_size,
0, false, true);
return 0;
}
EXPORT_SYMBOL(ceph_cls_assert_locked);

84
net/ceph/decode.c Normal file
View File

@ -0,0 +1,84 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/ceph/decode.h>
static int
ceph_decode_entity_addr_versioned(void **p, void *end,
struct ceph_entity_addr *addr)
{
int ret;
u8 struct_v;
u32 struct_len, addr_len;
void *struct_end;
ret = ceph_start_decoding(p, end, 1, "entity_addr_t", &struct_v,
&struct_len);
if (ret)
goto bad;
ret = -EINVAL;
struct_end = *p + struct_len;
ceph_decode_copy_safe(p, end, &addr->type, sizeof(addr->type), bad);
ceph_decode_copy_safe(p, end, &addr->nonce, sizeof(addr->nonce), bad);
ceph_decode_32_safe(p, end, addr_len, bad);
if (addr_len > sizeof(addr->in_addr))
goto bad;
memset(&addr->in_addr, 0, sizeof(addr->in_addr));
if (addr_len) {
ceph_decode_copy_safe(p, end, &addr->in_addr, addr_len, bad);
addr->in_addr.ss_family =
le16_to_cpu((__force __le16)addr->in_addr.ss_family);
}
/* Advance past anything the client doesn't yet understand */
*p = struct_end;
ret = 0;
bad:
return ret;
}
static int
ceph_decode_entity_addr_legacy(void **p, void *end,
struct ceph_entity_addr *addr)
{
int ret = -EINVAL;
/* Skip rest of type field */
ceph_decode_skip_n(p, end, 3, bad);
/*
* Clients that don't support ADDR2 always send TYPE_NONE, change it
* to TYPE_LEGACY for forward compatibility.
*/
addr->type = CEPH_ENTITY_ADDR_TYPE_LEGACY;
ceph_decode_copy_safe(p, end, &addr->nonce, sizeof(addr->nonce), bad);
memset(&addr->in_addr, 0, sizeof(addr->in_addr));
ceph_decode_copy_safe(p, end, &addr->in_addr,
sizeof(addr->in_addr), bad);
addr->in_addr.ss_family =
be16_to_cpu((__force __be16)addr->in_addr.ss_family);
ret = 0;
bad:
return ret;
}
int
ceph_decode_entity_addr(void **p, void *end, struct ceph_entity_addr *addr)
{
u8 marker;
ceph_decode_8_safe(p, end, marker, bad);
if (marker == 1)
return ceph_decode_entity_addr_versioned(p, end, addr);
else if (marker == 0)
return ceph_decode_entity_addr_legacy(p, end, addr);
bad:
return -EINVAL;
}
EXPORT_SYMBOL(ceph_decode_entity_addr);

14
net/ceph/messenger.c
View File

@ -199,12 +199,14 @@ const char *ceph_pr_addr(const struct ceph_entity_addr *addr)
switch (ss.ss_family) {
case AF_INET:
snprintf(s, MAX_ADDR_STR_LEN, "%pI4:%hu", &in4->sin_addr,
snprintf(s, MAX_ADDR_STR_LEN, "(%d)%pI4:%hu",
le32_to_cpu(addr->type), &in4->sin_addr,
ntohs(in4->sin_port));
break;
case AF_INET6:
snprintf(s, MAX_ADDR_STR_LEN, "[%pI6c]:%hu", &in6->sin6_addr,
snprintf(s, MAX_ADDR_STR_LEN, "(%d)[%pI6c]:%hu",
le32_to_cpu(addr->type), &in6->sin6_addr,
ntohs(in6->sin6_port));
break;
@ -220,7 +222,7 @@ EXPORT_SYMBOL(ceph_pr_addr);
static void encode_my_addr(struct ceph_messenger *msgr)
{
memcpy(&msgr->my_enc_addr, &msgr->inst.addr, sizeof(msgr->my_enc_addr));
ceph_encode_addr(&msgr->my_enc_addr);
ceph_encode_banner_addr(&msgr->my_enc_addr);
}
/*
@ -1732,12 +1734,14 @@ static int read_partial_banner(struct ceph_connection *con)
ret = read_partial(con, end, size, &con->actual_peer_addr);
if (ret <= 0)
goto out;
ceph_decode_banner_addr(&con->actual_peer_addr);
size = sizeof (con->peer_addr_for_me);
end += size;
ret = read_partial(con, end, size, &con->peer_addr_for_me);
if (ret <= 0)
goto out;
ceph_decode_banner_addr(&con->peer_addr_for_me);
out:
return ret;
@ -1981,6 +1985,7 @@ int ceph_parse_ips(const char *c, const char *end,
}
addr_set_port(&addr[i], port);
addr[i].type = CEPH_ENTITY_ADDR_TYPE_LEGACY;
dout("parse_ips got %s\n", ceph_pr_addr(&addr[i]));
@ -2011,9 +2016,6 @@ static int process_banner(struct ceph_connection *con)
if (verify_hello(con) < 0)
return -1;
ceph_decode_addr(&con->actual_peer_addr);
ceph_decode_addr(&con->peer_addr_for_me);
/*
* Make sure the other end is who we wanted. note that the other
* end may not yet know their ip address, so if it's 0.0.0.0, give

19
net/ceph/mon_client.c
View File

@ -39,7 +39,7 @@ static int __validate_auth(struct ceph_mon_client *monc);
/*
* Decode a monmap blob (e.g., during mount).
*/
struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
static struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
{
struct ceph_monmap *m = NULL;
int i, err = -EINVAL;
@ -50,7 +50,7 @@ struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
ceph_decode_32_safe(&p, end, len, bad);
ceph_decode_need(&p, end, len, bad);
dout("monmap_decode %p %p len %d\n", p, end, (int)(end-p));
dout("monmap_decode %p %p len %d (%d)\n", p, end, len, (int)(end-p));
p += sizeof(u16); /* skip version */
ceph_decode_need(&p, end, sizeof(fsid) + 2*sizeof(u32), bad);
@ -58,7 +58,6 @@ struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
epoch = ceph_decode_32(&p);
num_mon = ceph_decode_32(&p);
ceph_decode_need(&p, end, num_mon*sizeof(m->mon_inst[0]), bad);
if (num_mon > CEPH_MAX_MON)
goto bad;
@ -68,17 +67,22 @@ struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
m->fsid = fsid;
m->epoch = epoch;
m->num_mon = num_mon;
ceph_decode_copy(&p, m->mon_inst, num_mon*sizeof(m->mon_inst[0]));
for (i = 0; i < num_mon; i++)
ceph_decode_addr(&m->mon_inst[i].addr);
for (i = 0; i < num_mon; ++i) {
struct ceph_entity_inst *inst = &m->mon_inst[i];
/* copy name portion */
ceph_decode_copy_safe(&p, end, &inst->name,
sizeof(inst->name), bad);
err = ceph_decode_entity_addr(&p, end, &inst->addr);
if (err)
goto bad;
}
dout("monmap_decode epoch %d, num_mon %d\n", m->epoch,
m->num_mon);
for (i = 0; i < m->num_mon; i++)
dout("monmap_decode mon%d is %s\n", i,
ceph_pr_addr(&m->mon_inst[i].addr));
return m;
bad:
dout("monmap_decode failed with %d\n", err);
kfree(m);
@ -469,6 +473,7 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc,
if (IS_ERR(monmap)) {
pr_err("problem decoding monmap, %d\n",
(int)PTR_ERR(monmap));
ceph_msg_dump(msg);
goto out;
}

42
net/ceph/osd_client.c
View File

@ -171,14 +171,6 @@ static void ceph_osd_data_bvecs_init(struct ceph_osd_data *osd_data,
osd_data->num_bvecs = num_bvecs;
}
#define osd_req_op_data(oreq, whch, typ, fld) \
({ \
struct ceph_osd_request *__oreq = (oreq); \
unsigned int __whch = (whch); \
BUG_ON(__whch >= __oreq->r_num_ops); \
&__oreq->r_ops[__whch].typ.fld; \
})
static struct ceph_osd_data *
osd_req_op_raw_data_in(struct ceph_osd_request *osd_req, unsigned int which)
{
@ -478,7 +470,7 @@ static void request_release_checks(struct ceph_osd_request *req)
{
WARN_ON(!RB_EMPTY_NODE(&req->r_node));
WARN_ON(!RB_EMPTY_NODE(&req->r_mc_node));
WARN_ON(!list_empty(&req->r_unsafe_item));
WARN_ON(!list_empty(&req->r_private_item));
WARN_ON(req->r_osd);
}
@ -538,7 +530,7 @@ static void request_init(struct ceph_osd_request *req)
init_completion(&req->r_completion);
RB_CLEAR_NODE(&req->r_node);
RB_CLEAR_NODE(&req->r_mc_node);
INIT_LIST_HEAD(&req->r_unsafe_item);
INIT_LIST_HEAD(&req->r_private_item);
target_init(&req->r_t);
}
@ -4914,20 +4906,26 @@ static int decode_watcher(void **p, void *end, struct ceph_watch_item *item)
ret = ceph_start_decoding(p, end, 2, "watch_item_t",
&struct_v, &struct_len);
if (ret)
return ret;
goto bad;
ret = -EINVAL;
ceph_decode_copy_safe(p, end, &item->name, sizeof(item->name), bad);
ceph_decode_64_safe(p, end, item->cookie, bad);
ceph_decode_skip_32(p, end, bad); /* skip timeout seconds */
ceph_decode_copy(p, &item->name, sizeof(item->name));
item->cookie = ceph_decode_64(p);
*p += 4; /* skip timeout_seconds */
if (struct_v >= 2) {
ceph_decode_copy(p, &item->addr, sizeof(item->addr));
ceph_decode_addr(&item->addr);
ret = ceph_decode_entity_addr(p, end, &item->addr);
if (ret)
goto bad;
} else {
ret = 0;
}
dout("%s %s%llu cookie %llu addr %s\n", __func__,
ENTITY_NAME(item->name), item->cookie,
ceph_pr_addr(&item->addr));
return 0;
bad:
return ret;
}
static int decode_watchers(void **p, void *end,
@ -5044,12 +5042,12 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
const char *class, const char *method,
unsigned int flags,
struct page *req_page, size_t req_len,
struct page *resp_page, size_t *resp_len)
struct page **resp_pages, size_t *resp_len)
{
struct ceph_osd_request *req;
int ret;
if (req_len > PAGE_SIZE || (resp_page && *resp_len > PAGE_SIZE))
if (req_len > PAGE_SIZE)
return -E2BIG;
req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_NOIO);
@ -5067,8 +5065,8 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
if (req_page)
osd_req_op_cls_request_data_pages(req, 0, &req_page, req_len,
0, false, false);
if (resp_page)
osd_req_op_cls_response_data_pages(req, 0, &resp_page,
if (resp_pages)
osd_req_op_cls_response_data_pages(req, 0, resp_pages,
*resp_len, 0, false, false);
ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
@ -5079,7 +5077,7 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
ret = ceph_osdc_wait_request(osdc, req);
if (ret >= 0) {
ret = req->r_ops[0].rval;
if (resp_page)
if (resp_pages)
*resp_len = req->r_ops[0].outdata_len;
}

31
net/ceph/osdmap.c
View File

@ -1489,11 +1489,9 @@ static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
/* osd_state, osd_weight, osd_addrs->client_addr */
ceph_decode_need(p, end, 3*sizeof(u32) +
map->max_osd*((struct_v >= 5 ? sizeof(u32) :
sizeof(u8)) +
sizeof(*map->osd_weight) +
sizeof(*map->osd_addr)), e_inval);
map->max_osd*(struct_v >= 5 ? sizeof(u32) :
sizeof(u8)) +
sizeof(*map->osd_weight), e_inval);
if (ceph_decode_32(p) != map->max_osd)
goto e_inval;
@ -1514,9 +1512,11 @@ static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
if (ceph_decode_32(p) != map->max_osd)
goto e_inval;
ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr));
for (i = 0; i < map->max_osd; i++)
ceph_decode_addr(&map->osd_addr[i]);
for (i = 0; i < map->max_osd; i++) {
err = ceph_decode_entity_addr(p, end, &map->osd_addr[i]);
if (err)
goto bad;
}
/* pg_temp */
err = decode_pg_temp(p, end, map);
@ -1618,12 +1618,17 @@ static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
void *new_state;
void *new_weight_end;
u32 len;
int i;
new_up_client = *p;
ceph_decode_32_safe(p, end, len, e_inval);
len *= sizeof(u32) + sizeof(struct ceph_entity_addr);
ceph_decode_need(p, end, len, e_inval);
*p += len;
for (i = 0; i < len; ++i) {
struct ceph_entity_addr addr;
ceph_decode_skip_32(p, end, e_inval);
if (ceph_decode_entity_addr(p, end, &addr))
goto e_inval;
}
new_state = *p;
ceph_decode_32_safe(p, end, len, e_inval);
@ -1699,9 +1704,9 @@ static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
struct ceph_entity_addr addr;
osd = ceph_decode_32(p);
ceph_decode_copy(p, &addr, sizeof(addr));
ceph_decode_addr(&addr);
BUG_ON(osd >= map->max_osd);
if (ceph_decode_entity_addr(p, end, &addr))
goto e_inval;
pr_info("osd%d up\n", osd);
map->osd_state[osd] |= CEPH_OSD_EXISTS | CEPH_OSD_UP;
map->osd_addr[osd] = addr;

33
net/ceph/pagevec.c
View File

@ -10,39 +10,6 @@
#include <linux/ceph/libceph.h>
/*
* build a vector of user pages
*/
struct page **ceph_get_direct_page_vector(const void __user *data,
int num_pages, bool write_page)
{
struct page **pages;
int got = 0;
int rc = 0;
pages = kmalloc_array(num_pages, sizeof(*pages), GFP_NOFS);
if (!pages)
return ERR_PTR(-ENOMEM);
while (got < num_pages) {
rc = get_user_pages_fast(
(unsigned long)data + ((unsigned long)got * PAGE_SIZE),
num_pages - got, write_page ? FOLL_WRITE : 0, pages + got);
if (rc < 0)
break;
BUG_ON(rc == 0);
got += rc;
}
if (rc < 0)
goto fail;
return pages;
fail:
ceph_put_page_vector(pages, got, false);
return ERR_PTR(rc);
}
EXPORT_SYMBOL(ceph_get_direct_page_vector);
void ceph_put_page_vector(struct page **pages, int num_pages, bool dirty)
{
int i;

17
net/ceph/striper.c
View File

@ -259,3 +259,20 @@ int ceph_extent_to_file(struct ceph_file_layout *l,
return 0;
}
EXPORT_SYMBOL(ceph_extent_to_file);
u64 ceph_get_num_objects(struct ceph_file_layout *l, u64 size)
{
u64 period = (u64)l->stripe_count * l->object_size;
u64 num_periods = DIV64_U64_ROUND_UP(size, period);
u64 remainder_bytes;
u64 remainder_objs = 0;
div64_u64_rem(size, period, &remainder_bytes);
if (remainder_bytes > 0 &&
remainder_bytes < (u64)l->stripe_count * l->stripe_unit)
remainder_objs = l->stripe_count -
DIV_ROUND_UP_ULL(remainder_bytes, l->stripe_unit);
return num_periods * l->stripe_count - remainder_objs;
}
EXPORT_SYMBOL(ceph_get_num_objects);